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

The description discloses important behavioral nuances beyond annotations: it specifies partial merge ('merge parcial'), that null values remove fields ('null apaga o campo'), and batch support via ids. These traits are not provided by the annotations (which only indicate non-read-only, non-idempotent, non-destructive) and give the agent essential knowledge about side effects and semantics. It does not contradict annotations and adds value.

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 description is two short sentences that deliver the main action, parameter usage, and bulk support without redundancy. It is front-loaded with the core purpose and each sentence earns its place, providing essential information without unnecessary elaboration.

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?

Given the tool's complexity (7 params, no output schema), the description adequately covers the primary workflow: single partial update with null deletion, multi-update via array, and bulk via ids. It misses semantics for `account` and `metadata`, which may be optional or context-specific, but overall it provides sufficient context for an agent to understand and invoke the tool correctly in most scenarios.

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?

With schema description coverage at 0%, the description carries the burden of explaining parameters. It explains `object`, `id`, `data` (only fields to change, null deletes), `updates` (array of {id, data}), and `ids` for bulk. However, it omits any explanation for `account` and `metadata`, leaving those parameters undefined. The description adds value for core parameters but is incomplete, missing two of the seven.

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 explicitly states 'Atualiza um registro (merge parcial) por id' (Updates a record (partial merge) by id), giving a specific verb and resource with the key semantic of partial merge. This clearly distinguishes it from sibling tools like crm_create_records or crm_delete_records by focusing on update semantics. The mention of null deletion and bulk support further clarifies scope.

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 description provides clear usage guidance by instructing to pass 'object, id e data' for single updates and 'updates' for multiple, plus 'Bulk support: accepts ids for batched execution.' This conveys when to use the tool for partial updates and bulk operations, though it does not explicitly compare with alternatives like create or delete, so it lacks explicit exclusions. The context is clear enough for an agent to infer use cases.

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