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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new context: the shape of the returned records (each value with its source URL) and a per-call price of $0.002, which agents need for cost planning. It says nothing about behavior on ambiguous names or on identifiers that resolve to multiple issuers, which is the main failure mode for a crosswalk.

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 input/output contract is front-loaded in the first clause, followed by audience/use case and then pricing on its own line so cost is easy to find. Slightly dense in the middle (the long output enumeration), but no sentence is redundant.

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?

With no output schema, the description carries the burden of describing returns and does so concretely, including source URLs per value. Combined with full schema coverage on inputs and annotations covering safety, an agent has enough to call it correctly; only the ambiguity/error path and 'auto' detection behavior are left open.

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% and the schema itself documents idType, exchange (with Bloomberg and MIC codes) and the identifier formats in detail, so the description only needs to reinforce. It does confirm that exactly one identifier is expected ("One identifier in") and enumerates the accepted identifier kinds, but it never explains the 'auto' default in idType or how detection works. Baseline 3 applies.

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 specific verb-and-resource pair: it takes one of six identifier types (ISIN, LEI, CIK, ticker, FIGI, name) and returns the full crosswalk (legal name, LEI, CIK, per-exchange tickers, ISINs, FIGIs, CFI, EU venues). That is clearly distinguishable from every sibling, which are domain tools (filings, sanctions, tenders), not identifier joins.

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?

It names concrete situations where the tool applies (KYC, portfolio data, filings research, joining datasets keyed differently) and implies it is the entry point before domain-specific siblings. It stops short of explicit routing, e.g. no instruction on when to prefer sec_company_screen to discover a CIK first, or what to do when a name is ambiguous.

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