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

Annotations declare readOnlyHint=false and idempotentHint=false, and the description usefully adds that successful deliveries are persisted privately to the account and consume shared research credits — cost and side-effect context the annotations do not convey. It also warns that matches are not thematically relevant, an important semantic limitation, though it omits failure modes and whether partial results are billed.

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, purpose first, with each subsequent sentence adding a distinct fact (matching semantics, delivery persistence and credit cost). Dense but front-loaded and free of filler, though the opening sentence packs several concepts together.

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 values need not be explained, but the tool is high-complexity (9 params, nested selector grammar, fresh/captured bases) and the description addresses none of that structure. It also omits how this fits the discover → measure → read research pipeline, leaving a large gap for such a complex operation.

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?

With nine parameters, deeply nested selectors, and only 22% schema description coverage, the description must carry parameter meaning, but it explains almost nothing. It gestures at 'explicit stored-data scope' (scope/select) and 'attached/unattached' (discover.entity, include_unattached) yet says nothing about basis.mode fresh vs captured, retain, delivery limits, or how selectors compose.

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 states a specific verb and resource: 'Find attached asset or author candidates and separately labelled unattached matches.' It implicitly distinguishes itself from measure_evidence and read_evidence by framing itself as a discovery step, but it never names those siblings or clarifies the division of labour, so the differentiation is only partial.

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 explicit when-to-use guidance and no mention of the obvious alternatives in the sibling set (measure_evidence, read_evidence, search_authors). The clause 'Matching wording selects evidence; it does not establish thematic relevance' is a scoping caveat rather than routing guidance, leaving an agent to infer when this tool is the right entry point.

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