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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add beyond that. It does: it discloses a freshness precondition (stale/missing facts invalidate a match) and a privacy boundary ("No patient data or contact details"), which the annotations cannot express. It stops short of describing what is returned when evidence is absent or partial.

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 short sentences, zero filler, with the primary action front-loaded and the freshness constraint before the privacy note. Every clause carries information the agent cannot get from structured fields.

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?

The enumerated return concepts (sources, scope, review dates, confidence, limitations) usefully stand in for the absent output schema. But with no output schema and one entirely undocumented parameter, the definition leaves a real gap around what topics filtering does and what a no-evidence result looks like.

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 two parameters, so the description must carry the meaning. It partially defines product_id as "one reviewed EMR product ID," but the topics parameter (a 9-value enum filter) is never mentioned, so the agent cannot tell whether topics narrows scope, is required, or affects which evidence is returned.

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?

"Retrieve claim-level sources, scope, review dates, confidence, and limitations for one reviewed EMR product ID" gives a concrete verb (retrieve) and a precisely bounded resource (evidence/provenance for a single product record). It is clearly not the same as find_emr_options or compare_emr_options, though it never names those siblings explicitly.

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?

"Stale or missing facts cannot support a match" implies this tool must be consulted before asserting a match, which is a real usage cue. However, there is no explicit when-to-use/when-not-to-use statement and no named alternative (e.g., use get_emr_vendor for profile fields), leaving the routing to inference.

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