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

Goes well past the readOnly/openWorld annotations: per-item credit cost, a 429 batch_exceeds_quota refusal with max_items_now, request-order results with found/not_found/error/timeout statuses, and precise idempotency replay semantics including 409 while running and 422 on differing items. It also discloses fuzzy name matching limits (best match only, no similar-spelling fallback).

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 core capability is front-loaded in the first clause and nearly every detail is operationally useful. It is, however, one dense run-on sentence chain, so the quota, credit and idempotency facts are harder to scan than they need to be.

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 return contract itself: result ordering, the four status values and the shared company object shape. Combined with the cost and quota behavior, an agent has everything needed to call it and interpret the response.

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 a rule the schema cannot enforce: each item needs country plus either an identifier (company_number, with nif/siren/vat aliases) or a name. It also explains match_score and the 24h idempotency-key replay window beyond the schema's terse field note.

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 ('Resolve up to 100 companies in ONE call') and even names the endpoint. The batch scope plus the sibling reference (companies_search's company object) makes clear this is the bulk counterpart to the search/identifier tools.

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 batch-of-100 framing implies when to prefer it over single-record siblings like company_by_identifier or companies_search, and it notes the result objects match companies_search. It never explicitly says 'use companies_search instead when X', so routing is inferred rather than stated.

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