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

Annotations already signal read-only, idempotent, open-world, and non-destructive behavior, so the bar is lower, but the description adds substantial behavioral context beyond those annotations: cascading internal lookups, source-labelled identifiers, explicit `unresolved` reporting, no assertion on ambiguous matches, and graceful degradation of enrichment. This gives an agent real expectations about how the tool behaves, not just what it returns.

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 front-loaded with trigger phrases and the core directive, and nearly every clause carries operational value. However, the 'company' branch is one extremely long nested parenthetical that is harder to scan, and some details could be consolidated without losing meaning. It earns its length but is not a model of concise structuring.

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, yet the description explicitly enumerates the return expectations: CIK, ticker, company_name, LEI with ownership relationships, FIGI, `figi_candidates`, source labels, `unresolved`, and for drugs the RxCUI, ingredient, brand, and RxNorm citation. It also covers failure modes such as degraded enrichment and ambiguous matches. For a two-parameter tool, this is essentially complete.

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 for the two parameters is already 100%, so the baseline is 3, but the description meaningfully exceeds the schema by explaining that company accepts ticker, CIK, ISIN, or name, while drug accepts brand or generic. It also includes critical warnings such as passing the entity name only and never trailing security-class words, plus ISIN-to-LEI semantics for non-US issuers. This is a strong compensation beyond minimal schema descriptions.

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 opens with concrete utterance patterns ('What's the ticker for…', 'find the CIK for…') and states a specific action: resolve a user-spoken name to canonical identifiers that other tools require as input. It explicitly scopes supported types ('company', 'drug') and positions itself among siblings by saying 'Use FIRST whenever you have a name but need an ID.' This makes it easy for an agent to distinguish from profile, compare, and search tools.

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 gives explicit trigger conditions ('Use FIRST whenever you have a name but need an ID') and covers important edge cases, such as returning `figi_candidates` for ambiguous instrument names and degrading gracefully when GLEIF/OpenFIGI are unavailable. It does not, however, explicitly name sibling tools to avoid, so the 'when-not / alternatives' guidance is partial rather than exhaustive.

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