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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real context beyond that: it distinguishes curated records (targets with action, effect, evidence grade, PubMed ids, binding values from IUPHAR/BPS, measured cultivars, cautions, citation) from thinner database records, and sets scope boundaries with 'Educational reference, not medical advice. No doses.' It does not state what happens when an id is not found or ambiguous.

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?

The trigger is front-loaded in the first sentence and the record contents follow in a logical order. The payload enumeration is dense and long for a single-parameter read, but each clause describes a distinct part of the return value that has no output schema to carry it, so the length is largely earned.

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 no output schema, the description carries the full burden of describing return values and does so thoroughly, covering both record variants and the fields within each. Scope limits (no doses, not medical advice) are stated, which is important for a pharmacology reference 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 100% and the schema's id field already lists every accepted format with examples, so the description is largely restating it. The added 'Example arguments: {"id":"cbd"}' gives a usable call shape but no new constraints or normalization rules (e.g. case sensitivity, whether 'CID 16078' with the prefix is accepted) beyond the schema.

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 — retrieving the full record of one compound — and enumerates the accepted key types (Greencyclepedia id, Cannabis Compound Database id, name, PubChem CID). It also distinguishes the two record shapes it may return (curated vs. database compound), which lets an agent separate it from search_compounds or compare_compounds without opening the schema.

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 opens with an explicit trigger: 'Use when asked what does THC, CBD or myrcene do in the body', which is a concrete when-to-use condition. It does not name an alternative sibling (e.g. search_compounds for lookups by partial name, or compare_compounds for multi-entity questions), so routing for those cases is left to inference.

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