get_decision_evidence

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 well: it states the operation writes, signs and executes nothing; enumerates the required environment settings TRUST_GATE_API_URL, TRUST_GATE_API_KEY and TRUST_GATE_TENANT_ID; specifies that tenant comes from configuration and never from an argument; and discloses the OK/REFUSED/UNAVAILABLE outcome model with the guarantee that missing config or errors yield UNAVAILABLE rather than fabricated data.

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 purpose is front-loaded and every sentence adds a real constraint (read-only, env vars, status semantics, API version dependency). The prose is slightly dense and the opening clause is grammatically tangled, but there is no filler.

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?

An output schema exists, so return-value detail is not strictly required, and the description still adds useful status semantics. The decisive gap is the opaque nested `request` parameter and the absence of any routing hint against sibling evidence tools, which leaves an agent unable to construct a correct call from the definition alone.

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?

The single parameter is an untyped object with additionalProperties allowed and 0% schema description coverage, so the description must compensate and does not. Phrases like 'the facts you supply' and 'the records you supply' gesture at its contents without naming a single field, shape, or required key inside `request`.

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 first sentence names the resource (evidence view, verdict, open questions for one decision) and the scope (the facts you supply), which is specific enough to distinguish it from a plain decision read. However, it never names or contrasts the near-identical siblings get_intervention_evidence and get_receipt_evidence, so an agent must guess which evidence tool to pick.

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 establishes that this is read-only and touches nothing, but gives no explicit when-to-use guidance and no alternatives among 15 siblings. It also does not say when NOT to call it (e.g. versus replay_decision for re-execution or verify_receipt for signature checking).

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