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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false, and openWorldHint=true. The description adds meaningful context beyond those annotations: it requires Operate access, may incur cost or affect live apps, applies the same permission checks as the app, and never returns secrets. It stops short of explaining confirmation requirements or the full consequences of destructive calls.

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 front-loaded with the core action and immediately follows with access requirements and risk warnings. The long categorical list of domains is somewhat broad and ends with 'and more,' but it still communicates scope without burying the essential information.

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 generic write-passthrough tool with five parameters, nested body/query objects, and sibling tools like api_catalog and api_schema, the description should explain how an agent discovers valid method/path combinations and request bodies. It provides a documentation URL and useful risk/security context, but omits routing to the catalog/schema tools and does not describe return behavior beyond 'Secrets are never returned.'

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 80%, so the schema itself documents most parameter meaning, including body, path, query, method, and workspace. The description only repeats the allowed mutation methods and does not add semantics for path, body, query, or workspace. The baseline 3 is appropriate because the schema carries the parameter documentation.

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 gives a clear verb and resource: it runs one mutation (POST, PUT, PATCH, or DELETE) against The Deployer's app with the app's own permission checks. It also scopes the domain broadly. It does not explicitly distinguish this generic mutation tool from sibling action tools or api_read, but the method enum makes the write-only nature clear.

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?

Usage is implied by 'Runs one change' and the write-only method enum, and the description gives the prerequisite 'Needs Operate access' plus a warning that some changes cost money or affect a live app. It does not say when to use this instead of specific sibling tools such as create_project, set_env, or deployment, nor does it mention api_catalog or api_schema for discovering valid operations.

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