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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes further by enumerating the payload: identity, targets/effects with evidence grades, measured binding values, cautions, all sources with PubMed ids and links, citation line, and canonical URL. It also sets expectations with 'Educational reference, not medical advice. No doses.' The notable omission is failure behavior — nothing says what happens for an unknown or malformed id.

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 usage condition, then the return payload, then the disclaimer, so a reader can stop early. It is one dense paragraph, though, and the payload enumeration plus the trailing example argument would scan better as a short list; the 'No doses' line is also slightly redundant with 'not medical advice.'

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?

With one parameter and no output schema, the description correctly shoulders the job of describing return contents, and it does so thoroughly. What remains unstated is edge behavior (invalid id, no match) and any sense of response size or pagination for records with many sources — the only meaningful gaps for a single-record lookup.

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%, so the baseline is 3, but the description earns above baseline by documenting the id prefix namespace and giving a concrete call: {"id":"compound:cbd"}. That tells the agent ids are typed composites rather than opaque handles, which the schema's single example does not convey.

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 gives a specific verb and resource — 'the full text of one Greencyclepedia record by the id that search returned' — and enumerates the id families (compound:, target:, condition:, trial:, cultivar:) so the agent knows the tool is cross-entity. It clearly separates itself from search. It does not, however, resolve the overlap with type-specific siblings like get_compound, get_target, and get_cultivar, which appear to retrieve the same records.

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?

'Use when search has returned an id and you want the whole record' gives an explicit trigger condition and implies the prerequisite step (search first). No exclusion is stated, and it never says why an agent would pick this over get_compound or get_target for the same id, so the routing among siblings is left partly to inference.

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