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

The annotations already mark readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, providing the safety profile. The description goes substantially beyond this by revealing internal cascading lookups, graceful degradation when external sources are unavailable, how identity resolution handles ambiguity (returns figi_candidates instead of asserting), and that unresolved identifiers are explicitly listed rather than omitted. It also labels each identifier with its source and explains the ISIN-to-LEI mapping for non-US issuers. This is rich behavioral detail that helps the agent predict outcomes.

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 long, but it packs a high density of information: examples, usage instruction, supported types, edge cases, and degradation behavior. It is well-structured with the primary usage directive near the beginning and detailed type-specific guidance later. It could be slightly trimmed for conciseness (e.g., some parenthetical asides), but every sentence contributes to correct usage. It earns a 4 for being effectively structured without excessive fluff.

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?

Given the tool's complexity (two entity types, multiple external sources, cascading lookups, ambiguity handling) and no output schema, the description is remarkably complete. It covers input formats, interpretation of ambiguous inputs, degradation behavior, unresolved identifier semantics, source labeling, and the distinction between entity resolution and security resolution. An agent would have clear expectations about what the tool returns and how to handle edge cases. There is no missing critical information for effective invocation.

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% for both parameters, but the description adds essential semantics beyond the schema. For 'type', it clarifies the meaning of 'company' and 'drug' and what each resolves to. For 'value', it gives concrete examples ('AAPL', '0000320193') and critical guidance on passing only the entity name, not the full noun phrase, with a specific warning about trailing security-class words. This level of detail is far more actionable than the schema's brief 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 example queries and states the exact action: resolving user-spoken names to canonical/official identifiers that other tools require as input. It explicitly differentiates itself from siblings by noting that other tools depend on these IDs, and it covers two distinct entity types (company, drug) with detailed scope. This is a specific, unambiguous statement of purpose.

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 contains a direct instruction: 'Use FIRST whenever you have a name but need an ID.' It also explains when it should be preferred (replacing 2-3 manual lookups) and covers important caveats (e.g., non-equity instruments, ambiguous names returning candidates, graceful degradation). While it doesn't name specific alternative tools, the 'use FIRST' directive and the emphasis on being the canonical name-to-ID resolver make usage guidance explicit and actionable.

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