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

The description explicitly claims 'Side-effect free', but the annotations declare readOnlyHint=false, which signals the tool may modify state. This is a direct contradiction between the description and the annotations, making it unsafe for an agent to rely on the stated side-effect behavior.

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 a single dense sentence with no filler. Purpose, validation behavior, the key 'enabled' semantics, side-effect safety, and invocation method are all front-loaded and useful.

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 core usage is covered well, especially the config semantics and side-effect-free guarantee. But there is no output schema and the description never explains what the preview returns or how the agent should interpret the response, leaving a meaningful gap for a tool whose whole purpose is to produce a preview.

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 0% schema description coverage, the description adds real meaning to the config parameter: it is validated against the agent's declared schema, enabled is a first-class key, and { enabled: false } is the off switch. However, request_id and idempotency_key remain completely undocumented, and built_in_agent_id is only implied by the tool name.

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 says it previews configuring a built-in agent, names the resource, and emphasizes that nothing is changed yet. This makes the dry-run nature obvious and distinguishes it from the applying sibling (configure_bind).

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 gives clear context: use this to preview and validate config before applying, with no side effects, and pass config via --body-json. It does not explicitly name the apply alternative or state when not to use it, so it stops short of a 5.

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