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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds real context: it hits an external Brazilian government-derived API and mutates linked contacts, a side effect beyond the company record itself. It omits whether existing field values are overwritten and what happens if the CNPJ is not found, which matters for a mutation tool.

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?

Three compact sentences with no filler: action and source first, then populated fields, then the contact-propagation side effect. Every clause carries information an agent needs.

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 enumerated field list effectively tells the agent what the call produces, and the side effect on contacts is disclosed. Missing only failure behavior and overwrite policy for a two-parameter mutation against an external API.

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 both parameters are documented there, so the description adds little beyond restating that CNPJ is the lookup key. It does not clarify normalization/format expectations for CNPJ or what happens when the supplied CNPJ conflicts with the stored one, which would have justified a higher score.

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 (enrich), resource (company), and the exact external source (Receita Federal / BrasilAPI via CNPJ), then enumerates the fields it populates. The added clause about propagating razão social/CNPJ to linked contacts distinguishes it from plain reads like get_company or writes like create_company.

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 context for use is clear: populate a company record from an official CNPJ lookup, with the lookup key optionally taken from the stored record. It does not name alternatives (e.g., manually updating via update_company) or state when not to run it, so it stops short of explicit routing.

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