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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's added value is in result semantics: salt/form family pointers are 'labeled, never merged,' which tells the agent how records relate. It also discloses provenance (OpenRemedies, RxNorm-mapped), though it omits behavior on no-match or ambiguity beyond returning candidates.

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-loads the verb and resource in the first clause, then adds behavior, routing, and provenance in tight succession. The semicolon-heavy first sentence is dense but every clause carries information; no filler.

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 resolution tool with rich annotations but no output schema, the description covers purpose, input forms, result structure (pointers labeled, never merged), and provenance. The main remaining gap is what happens when no or multiple candidates match, but the limit parameter and 'resolve' framing imply candidate handling.

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%, with q and limit already documented. The description restates the accepted name forms for q but adds no syntax, normalization, or limit semantics beyond the schema, so baseline 3 applies.

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 and resource: 'Resolve a drug/herb/supplement name ... to substance records,' and explicitly lists accepted name forms (generic, brand, botanical). It distinguishes itself from siblings by declaring it is the 'first step' and returns 'the substance_id the other tools take,' which clearly separates it from get_substance_uses and resolve_entity.

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 trigger condition: use as the first step for 'what is <drug / herb / supplement> used for or approved for' questions. It does not state when not to use it (e.g., when a substance_id is already known) or name downstream alternatives explicitly, but the routing guidance is clear.

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