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

Annotations only flag safety ('readOnlyHint': false, 'destructiveHint': false) and openness; the description adds what they cannot: this is asynchronous, returns a jobId immediately, takes roughly 1–3 minutes, and must be polled rather than awaited. That timeouts motivated the design is exactly the kind of behavioral context an agent needs to choose correctly.

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 sentences, front-loaded with the action and the immediate return, then the routing rule, then the polling cadence. Every clause carries distinct operational information with no padding.

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 job-starter with no output schema, the definition covers the trigger, the return value (jobId), the latency, and the terminal step (get_website yielding finished HTML). Nothing needed to call it correctly or complete the loop is absent.

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%, so the brief/style/deliver_email documentation is already complete and enum-like style options are listed. The description's only addition is 'Same options as generate_website', a cross-reference that adds no syntax or format detail, so the 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?

The definition pairs a specific verb and resource ('Start generating a full website from a brief') with unusual scope detail: the immediate jobId return and the 1–3 minute background duration. It also explicitly names the sibling it replaces, so an agent can distinguish it from generate_website without opening either schema.

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?

'USE THIS instead of generate_website for any real build — it avoids the client timeout' states the selection rule outright, including the reason. The follow-up path is spelled out too ('call get_website with the returned jobId every ~20–30s'), leaving nothing about the workflow to inference.

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