update_csp

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

The description adds significant behavioral context beyond the annotations: it explicitly warns that 'rules é SUBSTITUÍDO, não mesclado' (rules are replaced, not merged), and that fields outside the contract are silently accepted and become inert. This is critical side-effect information that the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true) do not convey. The description also points to a schema URI for further details, exceeding the baseline.

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 well-structured: a clear opening sentence, a critical warning with an emoji for emphasis, and a bullet list of optional fields. Every sentence adds value—no fluff. The most important caveat (rules replacement) is front-loaded, and the list of common fields is concise and actionable.

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?

The description is quite complete for an update tool: it covers the main behavior, the rules replacement, and useful field hints. However, it does not mention expected response or errors, and it doesn't explicitly state success criteria. Given the complexity and absence of an output schema, a 4 is fair—there's a small gap but nothing that would mislead an agent.

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?

Although the schema covers 100% of parameters, the description adds substantial semantics for the 'rules' parameter, explaining the replacement semantics and listing the most-used behavior fields (must_not_tools, max_iterations, etc.). It also clarifies that extra fields are inert. This goes well beyond the schema definitions and helps agents construct valid payloads.

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 action: 'Atualiza uma política de segurança existente' (updates an existing security policy), specifying the verb, resource, and that it's for existing policies. This distinguishes it from create_csp, delete_csp, and toggle_csp. The purpose is unambiguous and context-specific.

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?

It provides explicit usage guidance: 'Envia apenas os campos que deseja alterar' (send only the fields you want to change) and warns about the rules replacement behavior. It also references create_approval_policy for approval fields, which is an alternative tool. However, it doesn't explicitly state when NOT to use this tool (e.g., for creation) or list all alternatives, so a 4 is appropriate.

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