triz_function_model

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so thoroughly. It discloses failure behavior ('fails closed with ok:false' for dangling, mis-directed, or mistyped wires), bounded-search behavior ('decided:false if the bounded search runs out'), nested-model limitations ('incompleteHierarchy lists them... their inner loops and contradictions are not analysed'), and that 'no weight is ever filled in.' It also states that each verdict cites its theorem basis.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph with no wasted sentences; each clause describes a distinct analysis or constraint. It is front-loaded with the core purpose, but the wall-of-text format reduces readability for a complex tool. Structure could be improved with bullets or sentence breaks, though the content earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, lack of output schema, and lack of annotations, the description is remarkably complete. It covers the analyses performed, failure modes, nested-model caveats, comparison behavior, isomorphism semantics, mpv_weights handling, and the 'basis' citation for each verdict. An agent has enough information to invoke it correctly and interpret key outcomes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it explains that box_map is 'applied before comparing deliverables' and should come from triz_transform outputs, that compare_to triggers a 'componentwise baseline-vs-concept comparison plus an isomorphism check,' and that mpv_weights limits comparison to named cost dimensions or 'harmful' with explicit weighted sums and no auto-filled weights.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Check a TRIZ function model written as a typed wiring diagram ... and analyse it.' It enumerates the analyses performed, including harm loops, ideality profile, separation checks, baseline-vs-concept comparison, and isomorphism check, making the tool's scope clear. It explicitly distinguishes from triz_expand_hierarchy for nested models, but does not route away from overlapping siblings like triz_isomorphism or triz_separate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives one explicit alternative: 'when boxes declare an `inner` model ... run triz_expand_hierarchy on each first.' It also frames harm loops as 'hypotheses about mechanism to substantiate, not findings,' clarifying interpretive use. However, it offers no when-not guidance or explicit comparison to siblings that perform standalone isomorphism or separation checks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.