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

The description states 'anonymize (id, LGPD, irreversível)' indicating the operation is irreversible, while the annotation destructiveHint is false. This is a direct contradiction; the annotation implies the tool is not destructive, but the description says it is irreversible. Additionally, the description does not disclose other behavioral aspects such as side effects, permission requirements, or what happens to associated data. With readOnlyHint false, it is clearly a write, but the irreversibility is not reflected in annotations.

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 not concise; it lists four actions when the tool is specifically for anonymize, adding noise. The structure with bullet points and '[Flattened action: anonymize]' is somewhat clear but unnecessarily verbose. A simple statement like 'Anonymize a Guru contact (LGPD, irreversible). Accepts id or ids for batch.' would be more efficient and focused.

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 has 4 parameters, no output schema, and weak annotations, the description is insufficient. It mentions LGPD and irreversibility but does not explain the intended use case, prerequisites, or consequences beyond irreversibility. It lacks details about return value, error conditions, or how the anonymization affects related data. The bulk support is mentioned but not elaborated (e.g., limits, behavior). Overall, the description does not provide enough context for reliable invocation.

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 is 0%, so the description must compensate. The description mentions id and ids (for bulk), but does not explain the data or account parameters. For an anonymize operation, data and account remain ambiguous; they might be irrelevant or required but unexplained. The description provides some meaning for id (the contact to anonymize) and ids (batch), but leaves the other half undocumented.

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 lists multiple mutation actions (create, update, anonymize, create_etickets) but does not explicitly state that this tool is specifically for anonymization. The flattened action annotation provides a hint, but the description's main clause is generic ('Mutações em contatos Guru') and lists several actions, obscuring the singular purpose of anonymizing a contact. It does mention 'anonymize (id, LGPD, irreversível)' which clarifies the function, so it is not a tautology but lacks a clear, focused statement.

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?

There is no explicit guidance on when to use this tool versus alternatives like guru_contacts_write_update or guru_contacts_write_create. The description mentions bulk support but does not compare with other contact mutation tools or explain scenarios where anonymization is appropriate. The list of actions (create, update, create_etickets) in the description could mislead an agent into thinking this tool performs all those actions, rather than being solely for anonymize.

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