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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is known. The description goes far beyond that: it explains internal cascading of multiple endpoints, graceful degradation when GLEIF or OpenFIGI are unavailable, how identifiers are labeled by source, and how unresolved identifiers are explicitly listed. This is exactly the kind of context that saves an agent from misinterpreting results.

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 every clause earns its place given the tool's complexity. It front-loads the purpose with example queries, then organizes the supported types and their nuances in a readable structure. It could arguably be tightened, but the density is justified; the structure and flow make it usable rather than overwhelming.

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 two entity types, multiple upstream sources, and important edge cases, the description covers everything an agent needs to call it correctly: the behavior on multiple matches, the fallback behavior, the output fields like `figi_candidates` and `unresolved`, and even the fact that it replaces 2-3 manual lookups. Although there is no output schema, the description communicates the critical aspects of the return shape.

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, but the description adds meaning that would be impossible to infer from the schema alone. It clarifies that 'value' for a company can be a ticker, CIK, ISIN, or name, and for a bond the value must be the issuer name as printed. It warns against passing the full noun phrase and gives an example. This is rich, actionable semantics.

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 states a very specific verb ('resolve'), a resource (names to canonical identifiers), and gives concrete example queries that signal exactly when to use it. It clearly distinguishes itself from siblings like entity_profile or compare_entities by framing it as the 'first' step when you have a name but need an ID.

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?

Explicit 'Use FIRST whenever you have a name but need an ID' tells the agent when to reach for it. It gives detailed input formatting rules (e.g., pass issuer name only, not the full noun phrase), and walks through the two supported types and their sub-types. It even covers the multi-match case and what the tool returns versus what it does not assert.

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