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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description goes well beyond that by disclosing the grounding constraint (answers only from records about entities the question names), the response contents, the fallback behavior on a miss, the 'no doses' scope limit and the educational-use caveat. That is meaningful context an agent could not derive from the annotations.

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?

It is front-loaded with the triggering condition and packs the routing, response shape and fallback into one paragraph with no filler. The trailing example argument duplicates the example already present in the schema description, and the run of colon-separated clauses about the return payload is dense, which costs it a point.

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?

There is no output schema, so the description carries the full burden of explaining returns, and it does so explicitly: evidence grade, findings with PubMed identifiers, source pages and cite_as with title, url, licence and accessed date. For a single-argument read tool, an agent has everything needed to decide to call it and to expect the right shape back.

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 coverage is 100% and the question parameter is already documented with a 300-character cap, so the schema does the heavy lifting and the baseline would be 3. The description adds value by clarifying that the question must name a compound, condition or receptor, and by repeating a concrete example argument that shows the expected phrasing.

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 (answer a plain question about compounds, conditions or receptors) and enumerates exactly what the answer contains: evidence grade, key findings with PubMed IDs, pages and cite_as. It also positions itself as 'the best first call', which separates it from the lookup siblings like get_compound or find_studies.

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?

It gives a clear triggering condition ('Use when you have a plain question such as ...') and labels itself the best first call, so an agent knows to reach for it before the narrower lookup tools. It also defines the miss case, saying it will report that nothing was found and suggest the closest names and tools. It stops short of naming specific alternative tools for follow-up, which keeps it at 4.

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