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

Goes beyond annotations by disclosing that execution is background/async, takes 'a few minutes,' and consumes no credits. These are exactly the behavioral facts an agent needs and that readOnlyHint=false / idempotentHint=true alone do not convey. It stops short of noting rate limits or whether overlapping calls are coalesced.

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?

Three short sentences, zero filler. The core action is front-loaded, followed by execution characteristics and the cost caveat. Every clause earns its place.

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 background mutation with a rich schema and an output schema already covering return values, the description supplies everything else the agent needs: async nature, latency expectation, follow-up step, and cost. 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 the domain_id field already documents its source ('from list_domains'), so the schema carries the semantics. The description adds nothing about the single parameter, which matches the baseline-3 expectation when the schema does the work.

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+resource: 'Queue a fresh crawl and re-score of a tracked domain's pages.' This cleanly distinguishes it from add_domain, remove_domain, list_domains, and get_scorecard among siblings. An agent immediately knows this triggers a recomputation rather than a lookup.

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?

Gives clear operational context: it is asynchronous ('runs in the background') and directs the agent to the follow-up tool ('read get_scorecard afterwards'). It lacks an explicit when-not or a statement of prerequisites beyond having a domain_id, so it falls short of the full when/when-not/alternatives pattern.

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