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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: fuzzy matching is supported, ambiguous matches are returned as multiple unmerged candidates (not silently collapsed), and the data provenance is OpenRemedies with MONDO mappings. It stops short of describing result ordering, scoring, or what an empty result means.

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 tight sentences, each carrying distinct information: what it matches, how ambiguity is handled, when to call it and what it yields, plus provenance. No filler and the when-to-use cue is front-loaded after the core definition.

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?

For a two-parameter lookup with no output schema, the description supplies everything an agent needs: that it is the first step for condition-scoped questions, that it emits condition_id consumable by other tools, how ambiguous input behaves, and where the data comes from. Nothing material is missing.

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 100%, so both parameters (q, limit) are already documented. The description's 'name/abbreviation/lay term/misspelling' phrasing restates the q schema description and adds no new guidance on how many candidates limit should be set to or how results are ranked.

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 (resolve) and resource (condition name/abbreviation/lay term/misspelling → condition concepts), and makes clear this is about conditions specifically, distinguishing it from resolve_substance and resolve_entity in the sibling list. The ambiguity-handling clause ('exposed as multiple candidates, never merged') further pins down what the tool returns.

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 a concrete triggering pattern: 'First step for any "medications, treatments or clinical trials for <condition>" question', and explains the downstream value (returns the condition_id other tools take). It does not explicitly route the agent to resolve_substance/resolve_entity for non-condition entities, so the sibling boundary is implied rather than stated.

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