input_schema
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-05.)
input_schema has 8 facts recorded in Dontopedia across 1 reference.
Mostly:has semantic meaning(1), part of(1), has level(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (3)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
hasPartHas Part(1)
- Tool Definition
ex:tool-definition
includesComponentIncludes Component(1)
- Tool Definition
ex:tool-definition
referencesConceptReferences Concept(1)
- Tool System Section
ex:tool-system-section
Other facts (7)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Has Semantic Meaning | defines tool parameters | [1] |
| Part of | Tool Definition | [1] |
| Has Level | 3 | [1] |
| Validates Input | Tool Execution | [1] |
| Data Type | object | [1] |
| Required in Schema | true | [1] |
| Schema Position | 3 | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (1)
ctx:discord/blah/agents/6- full textctx:discord/blah/agents/6text/plain1 KB
doc:discord/blah/agents/6Show excerpt
[2026-03-15 03:03] traves_theberge: The key insight: LLM + loop + tools = agent The Agent Loop The core while-loop Code: basic loop skeleton Stop conditions: end_turn, max_iterations, human approval Sampling (The Model Layer) Making API…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.