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

With readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false already in annotations, the description goes well beyond by disclosing concrete runtime behavior: returns identifiers labelled by source, explicitly lists unresolved identifiers under 'unresolved' instead of omitting them, returns 'figi_candidates' when a name matches multiple instruments, gracefully degrades when GLEIF/OpenFIGI are unavailable, and cascades through multiple endpoints internally. This gives strong transparency into input-to-output behavior with no contradiction against annotations.

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 dense and long, but nearly every clause adds necessary behavioral or parameter context. It is front-loaded with user-phrase examples and the 'Use FIRST' directive, then organized by supported type with explicit caveats. Some redundancy exists with the schema's value description (e.g., 'ENTITY NAME ONLY' appears in both), and the parenthetical-heavy style makes it slightly harder to scan, but the structure is logical and no sentence is ornamental.

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, so the description must carry the burden of explaining return behavior, and it does so in detail: CIK/ticker/company_name from EDGAR, LEI and ownership from GLEIF, FIGI from OpenFIGI, RxCUI/ingredient/brand from RxNorm, plus `unresolved` and `figi_candidates` cases. It also covers failure behavior, accepted identifier formats, and the practical benefit of replacing multiple manual lookups. For a tool with this much cross-source complexity, the description is remarkably 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?

The schema already describes both parameters and reaches 100% description coverage, but the description adds materially beyond the schema: it introduces ISIN as a valid company input, clarifies FIGI lookup behavior for non-ticker instruments, explains the 'ENTITY NAME ONLY' requirement and issuer-exact matching for bonds, and details the `figi_candidates` disambiguation path. These are not just restatements of the schema; they resolve real decision points an agent would face when populating `type` and `value`.

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 names a clear verb ('resolve'), a specific resource ('user-spoken NAME to canonical/official identifiers'), and explicitly frames the tool as the input provider for 'other tools require as input.' It also enumerates two distinct entity types, company and drug, and differentiates this resolver from sibling lookup/analysis tools through statements like 'Use FIRST whenever you have a name but need an ID.' This is far beyond a tautology and leaves minimal ambiguity about what the tool does.

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 provides detailed scoping for company vs drug lookups, including edge cases like non-equity instruments and ISIN-to-LEI resolution. It does not explicitly name sibling alternatives or state 'do not use when...', but the strong 'use first whenever' guidance plus the input-format details gives an agent clear situational direction.

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