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

With no annotations, the description carries the full disclosure burden and does add real behavioral facts: it is read-only, abstention strips only the verdict while evidence/reservations/gaps persist, no rank is emitted on overlapping intervals, and replay/attestation verdicts are as-of the last build. These are meaningful, but they are cryptic and omit permissions, cost, and what a consumer does with the result.

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?

Four compact sentences with the primary operation front-loaded (read-only decision for one category) followed by behavior and caveats. It earns its length, though the density of version tags slightly blurs the structure.

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 sketches the return shape (EVIDENCE/ABSTAIN plus reason_code), which is essential context. But given 4 parameters at 0% coverage and a nested object, the definition is still short of what an agent needs to invoke it correctly.

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 0% across 4 parameters, so the description must compensate and largely does not. "One category" loosely maps to `category` and "a declared context" hints at `constraints`, but `as_of` and `max_age_days` are never addressed, nor are the pattern constraints or the nested `constraints` object's value types.

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 does convey that this is a read-only decision engine producing an EVIDENCE or ABSTAIN verdict plus a reason_code for one category. However the core purpose is wrapped in opaque internal jargon ("decision.v1", "answer_rule.v3") that an outside agent cannot resolve, and it never plainly states the verb+resource. It distinguishes itself from siblings only implicitly.

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 when-to-use or when-not-to-use guidance, and no sibling (explain_limits, get_need, get_results, etc.) is named as an alternative. The agent is left to infer entirely when this tool is preferable to get_results or get_run.

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