Rename, toggle or redefine a rule

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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description's disclosure that the call is a write gated on confirm and that the operation has no server-side dry run adds real context beyond them. It loses a point because the 'preview is returned without confirm' behavior is already documented on the confirm parameter in the schema, making part of the statement redundant.

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?

Two clauses, both front-loaded with the action first and the write/confirm constraint second; no filler, no restating of the title, and every phrase carries information the agent needs before calling.

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 mutating, nested-body tool with no output schema, the definition states the endpoint, the fields it can change, and the confirm gate, which is enough to invoke it safely. It is not fully complete because it never says how omitted body properties are treated or what the preview response contains.

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?

At 50% schema description coverage, the description usefully maps its verbs onto the undocumented nested body fields: rename maps to name, toggle to enabled, redefine to definition. It does not clarify idempotencyKey or whether omitted body fields are left untouched, so the compensation is partial rather than complete.

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 concrete verbs (rename, toggle, redefine) tied to a specific resource and endpoint (PATCH /v1/rules/{id}), which lets an agent distinguish it from rules_create, rules_get and rules_delete. It falls just short of a 5 because it does not explicitly name those siblings or delimit the scope beyond the endpoint.

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 strongest usable guidance is the execution gate: nothing is sent unless confirm: true. However, there is no explicit routing advice about when to prefer rules_create versus this tool, nor any statement about prerequisites or partial-update expectations, so the when-to-use condition is only implied by the endpoint path.

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