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

Annotations already declare readOnly/idempotent/openWorld, but the description adds substantial process disclosure: it resolves identity via SEC, derives a distinctive name token, unions all sponsor_name variants in one call, and reports which forms were matched. It also discloses a non-obvious filtering rule (industry words like PHARMACEUTICALS never anchor a match, dropped substring hits counted in excluded_non_word_matches), which the agent could not infer from annotations or schema.

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 purpose and the 'use this instead' routing statement are front-loaded, and every later sentence (the Lilly example, the token-derivation rule, the excluded-match counter, the subsidiary fallback) carries distinct information. It is on the long side, but the length is justified by the non-obvious matching behavior; minor trimming of the example would still be possible.

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 tool with no output schema and a deceptively simple two-parameter surface, the description fills every gap: why the resolver exists, what the return payload contains (combined application list plus sponsor_name_forms breakdown and excluded_non_word_matches), and how to handle the subsidiary case. Nothing needed to invoke it correctly is missing.

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; however the description adds meaning beyond the schema by telling the agent which identifier to prefer and, critically, that a subsidiary/operating name must be resolved to the parent CIK via sponsor_to_filer before being passed. The example (Eli Lilly's own SEC name matching zero sponsor_name rows) makes the parameter's purpose concrete.

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 ('Find ALL Drugs@FDA applications for a company') and names the resolver inputs (SEC CIK, ticker, company name). It explicitly differentiates itself from the sibling fda_drug_approvals by explaining why the naive sponsor_name lookup fails there.

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 routing rule: 'Use this INSTEAD of guessing sponsor_name strings for fda_drug_approvals when you have (or can resolve) the company's CIK/ticker.' It also covers the subsidiary edge case and names the alternative tool (sponsor_to_filer) to resolve a parent first.

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