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

Annotations indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false, but the description does not contradict these. It adds some behavioral context by noting that 'update' only works with documents 'em andamento' (in progress) and that 'delete' is a soft-delete. However, it does not disclose other behavioral traits like authentication requirements, rate limits, or side effects beyond what is implied by the actions. Given the annotations are minimal, the description carries some burden but could be more explicit.

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 quite long and lists many actions and fields, which is necessary given the tool's multi-action nature. However, it is not well-structured: it uses a bullet-like format but is dense and could be more readable. The flattened action 'update' is noted at the end, but the description front-loads the general purpose and then lists all actions, which may be overwhelming. It earns its place but could be more concise by focusing on the primary action.

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 (multiple actions, nested objects, no output schema), the description provides a fair amount of detail about the fields for each action. However, it lacks information about return values, error handling, or prerequisites. The annotations are minimal, and the schema is very generic (data is an object with additionalProperties), so the description is the main source of guidance. It covers the actions but not the full context, such as authentication or rate limits.

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?

The input schema has 3 parameters (data, account, doc_token) with 0% schema description coverage. The description does add meaning by detailing the fields for each action, especially for 'update' which uses doc_token and data. However, the description is not structured per parameter; it lists fields in a compact format. For the flattened action 'update', it mentions 'doc_token' and 'data' but does not explain the 'account' parameter at all. Since schema coverage is 0%, the description must compensate, but it only partially does.

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 clearly states the tool's purpose: 'Criar/alterar documentos de assinatura no ZapSign' (Create/change signature documents in ZapSign). It lists multiple actions (create, create_from_template, update, delete, refuse, place_signatures, add_extra_doc) and specifies the flattened action as 'update'. This distinguishes it from sibling tools like zapsign_documents_write_create and zapsign_documents_write_delete, though the description covers more than just the update action, which slightly dilutes focus.

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 some usage context by listing the actions and their required fields, but it does not explicitly state when to use this tool versus alternatives. For example, it doesn't mention that for creating a document you should use zapsign_documents_write_create instead. The flattened action 'update' is noted, but there is no guidance on when to choose this tool over the more specific sibling tools.

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