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

With no annotations, the description carries full behavioral burden and does so: asynchronous execution ('takes seconds to minutes depending on the URL count'), the return value (run_id), the per-site concurrency constraint, and the required authorization scope (boosts:write). This is exactly the context an agent needs before invoking.

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?

Four short sentences, front-loaded with the core action and outcome, followed by asynchrony guidance, concurrency constraint, and auth requirement. No filler or redundancy.

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 an async mutation with no output schema, the description covers what is created, what is returned (run_id), how long it takes, how to poll results, the concurrency limit, and the required scope. Nothing material is missing.

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 100% and all four parameters (site_id, urls, region, variations) are documented in the schema itself. The description adds only the 'same-origin' constraint and site ownership notion, which are already implied by the schema text, so baseline 3 applies.

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?

States a specific verb and resource ('Warm (pre-cache) a list of same-origin URLs for one of your sites') and adds the concrete outcome ('Creates a warm run and returns its run_id'). An agent can distinguish it from list_warm_runs/get_run siblings purely from this text.

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?

Explicitly instructs to follow the call with list_warm_runs or get_run rather than assuming completion, and notes 'A site runs one warm at a time,' which tells the agent not to fire concurrent warms. It does not spell out when not to use this tool, 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.