fda_substance

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is fully disclosed. The description adds minimal behavioral context beyond the search syntax; it does not describe pagination, limits, or any non-obvious behavior. This is acceptable given the annotations, but the description doesn't contribute meaningful extra behavioral details, so a 3 is appropriate.

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 description is a single opening sentence, a short 'Search by' line, and four example search commands. The examples are useful and earn their place, though perhaps a couple of the examples could be trimmed. It is well-structured and front-loaded; each part serves the agent.

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 this simple search tool, the annotations cover safety and the schema covers both parameters. The description adds the domain-specific examples and data categories, which is sufficient for correct usage. It doesn't explain what output looks like (no output schema), but that's not required given the search-style tool and the fact that return values are fairly guessable.

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?

The schema covers both parameters, but the description enriches usage by providing concrete examples specific to the substance domain: 'names.name:"PARACETAMOL"', 'codes.code:"220127-57-1"', 'unii:"09211A0HHL"', 'structure.formula:"C6H12"'. This goes beyond the generic 'field:value' examples in the schema and directly helps an agent construct correct queries.

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 clearly states the tool's purpose ('Search FDA substance data — molecular-level ingredient information'), indicating the resource domain and the level of data. It distinguishes from other FDA tools like drug labels or adverse events by focusing on the substance identifiers (name, CAS, UNII, molecular formula). The verb 'Search' and the specific resource make it unambiguous.

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?

The description provides clear 'how-to' context (search by name, CAS, UNII, formula) and includes explicit example queries, giving strong practical guidance. However, it does not explicitly mention when to prefer this tool over other FDA search tools (e.g., fda_unii or fda_drug_labels), so it lacks the explicit 'when-not' or alternative direction that would merit a 5.

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