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

Goes well beyond annotations by disclosing key behavior: it executes with the website's secrets, makes real outgoing requests, and counts toward the plan's monthly calls. These are precisely the hidden costs/side effects an agent needs, complementing the destructive/openWorld/idempotent hints.

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 tightly written sentences with the core action front-loaded and zero filler; the secondary sentence adds the billing consequence. Slightly dense but efficiently so.

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 3-param invocation tool with no output schema, the description covers what it does and its real-world effects, with annotations carrying the safety profile. Minor gaps remain around payload/websiteId semantics and error/failure behavior, but nothing critical for correct invocation 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 coverage is 67% (name and payload documented, websiteId not), and the description adds no parameter-level detail. It explains the execution context but not how to format the payload or which function names are valid beyond 'an `http` server function'.

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: runs one of the draft site's `http` server functions and returns its result. The phrase 'exactly as page code on the draft would receive it' distinguishes it from siblings like websiteFunctions_runs_list/get, which inspect past runs rather than execute one.

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 scope is made clear ('on the draft', uses website's secrets, counts toward monthly calls), which implies when to use it, but there is no explicit when-to-use/alternatives guidance. It never tells the agent to prefer runs_list/runs_get for inspection or warns against using it casually given the billing impact.

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