triz_implementations

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

With no annotations, the description carries the full behavioral burden. It does add real value beyond the schema: it discloses that cross-mode splicing of behavior and cost is checked for, and that provenance stays user-declared rather than verified. It says nothing about whether the call mutates anything, what the verdict format is, or cost/limits of evaluation, leaving notable gaps for an annotation-free tool.

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?

Two tightly packed sentences with no filler, and the verb-plus-resource statement is front-loaded before the constraint. The phrasing is dense with domain jargon, but every clause carries information.

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?

For a tool whose schema is this deep (nested models, contracts, evidence, provenance) with no annotations and no output schema, two sentences are thin: the return shape is never described, the meaning of 'modes' and 'provenance remains declared' is left implicit, and the effort-bounding parameters are ignored. The rich nested schema covers much structural semantics, but the description does not fill the remaining gaps.

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?

Top-level schema description coverage is 0%, so the description must compensate, and it partly does: 'one whole-model behavior... and resource contract' maps onto the contract object's target/acceptable/allowed_harms/budget fields, and 'named complete implementations' maps onto alternatives[].id. The max_work and max_states parameters, which bound evaluation effort, are not mentioned anywhere in the description.

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 gives a specific verb ('Evaluate') and a specific resource ('named complete implementations'), and lists the four contract dimensions being checked (whole-model behavior, adequacy, declared-harm, resource). It could be sharper about how this differs from siblings such as triz_adequacy or triz_subsystem_contract, which also sound like contract checks, so sibling differentiation is not explicit.

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?

There is no statement of when to reach for this tool versus triz_adequacy, triz_evals, or triz_subsystem_contract, and no preconditions (e.g. that models must be reviewed rather than draft) are given in the description. The only guidance is a prohibition ('never splice behavior and cost from different modes'), which constrains how to call it rather than when to call it.

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