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

No annotations are provided, so the description carries the full burden, and it does well: it declares the tool is governed and deterministic, invokes no model, derives nothing from prose, accepts no dependency-addressed reports, and explains the lifecycle by which a dependency stops being reported. It stops short of stating read-only/permission characteristics in so many words, but the surrounding statements make side-effect-free behavior clear.

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?

Dense but well front-loaded: purpose first, then the deterministic/governance constraints, then the routing rule and the stop rule. Every sentence carries a distinct guardrail rather than filler, though the middle sentences are clause-heavy enough that a skim risks losing the usage rule buried after them.

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 must describe returns, and it does: nextInquiries, awaiting_evidence, evidenceRequirements, and admissibility.inquirableSubjectKinds are all named and explained, and the 'already evaluated questions are replaced by their blockers' note pre-empts a misreading. Complete enough for an agent to interpret the response shape.

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 coverage is 100%, so both parameters (subjectId, subjectKind) are already documented in the schema. The description mentions 'a subject' and points at admissibility.inquirableSubjectKinds for valid kinds, but adds no format or validation detail beyond the schema. Baseline 3 is correct.

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 opening sentence states precisely what the tool reports: what OEX has asked about a subject, what it could not conclude, why, and the next registered question. It explicitly contrasts itself with siblings ('not a work queue', 'use investigate_economic_question ... for the facts'), so an agent can place it against the other ~50 tools without opening a schema.

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?

Gives explicit routing to an alternative ('Use investigate_economic_question or the subject's own resource for the facts'), an explicit exclusion ('this is not a work queue ... carries no identifiers to act on'), and a stopping rule ('Follow only nextInquiries; awaiting_evidence means stop until admissible evidence changes'). This is about as complete as when-to-use guidance gets.

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