quipu_policy_check

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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description adds genuine context beyond them: determinism/reproducibility guarantees, that the verdict is returned UNSIGNED, that evidence_hash binds the result, and that a false evidence_probe downgrades 'unsatisfied' to 'unknown'. It does not cover cost, failure modes, or what happens with a non-existent policy IRI.

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?

Three sentences, front-loaded with the core action and result type, which is good structure. However, it is dense with unexplained internal jargon ('committed-tier', 'aegis:claim', 'graph of record', 'Phase-0 verifier registry') and the signing sentence, while informative, could be tighter.

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?

With no output schema, the description usefully describes the return value (Verdict with outcome enum and evidence_hash), which is the most important missing structured data. Gaps remain for a 7-parameter tool: tx, valid_at, and predicate_id are never discussed, and 'committed-tier' is never contrasted with other tiers.

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 all seven parameters are already documented in the schema, including the $target placeholder, the policy-vs-claim alternative, and the evidence_probe unknown semantics. The description reinforces the $target binding and claim/policy duality but adds no new syntax, defaults, or precedence rules beyond what the schema states.

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?

States a specific verb and resource: evaluates a governance Policy's aegis:claim (SPARQL ASK) over the committed graph and returns a Verdict with outcome and evidence_hash. The phrase 'signing + persistence is the Phase-0 verifier registry's job' implicitly separates it from quipu_verdict_verify, but no sibling is named explicitly, so an agent must infer the boundary.

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?

Usage is only implied by 'committed-tier evaluation' and 'any verifier re-running the same ASK'. There is no explicit when-to-use/when-not, no routing to quipu_ask for ad-hoc SPARQL or to quipu_verdict_verify for signature checking, and no stated prerequisites such as needing the policy already committed.

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