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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real context beyond that: the upstream data source (Bloomberg OpenFIGI), and the rate-limit tradeoff ('No API key required (optional key raises rate limits)'). One caveat -- the description describes reaching an external public API while openWorldHint is false, a mild tension worth noting, though not a direct behavioral contradiction.

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?

Front-loaded with purpose, then bulleted usage conditions, then the alternative, then source/rate-limit notes -- a clean scannable hierarchy with almost no filler. Minor waste in restating the return fields, which the output schema already supplies.

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 an external-instrument lookup with an output schema, the description supplies everything needed to select and invoke it: trigger conditions, the sibling to use otherwise, data source, and rate-limit behavior. The remaining gap is parameter-level guidance for a schema with many optional fields, which the description never addresses.

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?

Reported schema description coverage is 0% at the interface level, so the description is expected to carry parameter meaning and it largely does not. It implies a free-text search ('by name or keyword') and alludes to security types ('ETFs, options, futures'), but says nothing about limit, exchange_code, security_type filtering, or the fin-specific wrapper params (wholesaler_ids, source_resource_id, additional_display_fields).

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 ('Search Bloomberg OpenFIGI for financial instruments by name or keyword') and enumerates what comes back (FIGI, ticker, exchange, security type, composite FIGI). It is unmistakably distinct from the get_*/search_* siblings because it is scoped to instrument discovery, not holdings, filings, or pricing.

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 this tool when:' bullets cover the exact triggering conditions (company name but no ticker/FIGI, wanting all instrument types for a name, discovering associated securities) and it names the alternative -- MapInstrumentIds -- with the condition that selects it ('if you already have a specific ID to convert'). This is the textbook when/when-not/alternative pattern.

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