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

Annotations only declare the safety profile (readOnly, idempotent, non-destructive), while the description adds substantial behavior an agent cannot get elsewhere: the 100-tail cap with fleetTruncated, the 90-day CVA/idle-day vulnerability window, the explicit no-CPF guarantee, and that a brand spanning multiple CNPJs collapses into ONE group. It also explains the found:false outcome, which is critical for interpreting misses.

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 purpose is front-loaded, but the bulk is one ~150-word run-on sentence with nested parentheticals, and much of it re-enumerates return fields that an output schema already documents. It is dense rather than padded, yet the structure is heavy to parse and partly duplicates structured data.

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 complex Brazilian registry tool, the definition covers identifier handling, group aggregation, truncation, privacy limits and the not-found case, and safety is already carried by annotations with return shape by the output schema. Remaining gaps (e.g. what 'dominant RBAC' entails beyond the output schema) are minor.

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 description coverage for the single query parameter is already 100%, so the baseline is 3. The description still adds value by restating and expanding the accepted formats (brand/URL slug as in /operadores/<slug>, 14-digit CNPJ vs 8-digit root) and by clarifying that a spelling or CNPJ-root mismatch yields found:false.

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?

Names a precise verb+resource (company-side profile behind a Brazilian operator/owner group) and maps it to the public /operadores page, then enumerates exactly what the payload contains, which cleanly separates it from siblings like jt_owner_group, jt_operators_stats and jt_company_search. An agent can tell what it returns without opening the schema.

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 accepted query forms (slug, commercial/legal name, CNPJ or 8-digit root) strongly imply this is the identifier-based lookup, and the found:false note gives a failure condition. However, there is no explicit when-to-use/when-not statement and no sibling is named as the alternative for adjacent questions (e.g. individual owner fleets), so guidance stays implicit.

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