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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond them: results are ranked with rupture/tension medicines first, and the response mixes in standalone shortages not attached to any medicine — a non-obvious shape an agent must anticipate. The safety framing about not inferring substitutability is a substantive use constraint, not a restatement.

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?

Front-loaded with the core action and result composition, then the ordering rule, then the safety guardrail. The only mild redundancy is the closing 'Other medicines in the results are not alternatives', which re-states the earlier prohibition — defensible given the medical risk, but it is a repeat.

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 described, and annotations cover the safety profile. What the description does supply — ranking, mixed shortage records, and the no-substitution rule — addresses the highest-risk ambiguities. Remaining gaps (empty-result behavior, matching fuzziness, how limit interacts with the two result groups) are minor for a 3-parameter read tool.

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 67%: query and only_in_shortage are documented in the schema, limit is self-evident from default/min/max. The description restates that the query targets name or active substance, which duplicates the schema rather than adding syntax, accent, or matching-behavior detail. Baseline 3 is appropriate given the schema does most of the work.

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?

States a specific verb (search), a specific resource (French medicines / BDPM) and the two axes queried (name or active substance), plus what the result set contains (linked ANSM shortage per medicine, plus unlinked shortages matching the query). It is clearly a search tool rather than a detail lookup, so get_medicine_info and list_current_shortages are distinguishable, though no sibling is named 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?

Gives an explicit and emphatic when-not-to-use rule: never use it to recommend substitutes, alternatives, equivalents, dosage changes, or stopping treatment. It also explains ordering behavior (rupture/tension first), which helps interpret results. It does not, however, route the agent between this and get_medicine_info or list_current_shortages when those might be the better call.

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