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

Beyond the annotations (readOnly=false, idempotent=false), the description discloses that the build is asynchronous, spends credits on the authenticated account, and returns a buildId. This is meaningful behavior an agent cannot infer from the schema alone.

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 sentences, with the core action first and the async follow-up second. Every clause adds information: what it builds, what it costs, what it returns, and what to call next.

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 tool with one required parameter and rich schema descriptions, the description covers the critical non-schema facts: async behavior, credit cost, the buildId return value, and the get_build_status polling path. No essential guidance 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%, so the schema already documents prompt, mode, framework, and the confirmation flag. The description adds no parameter-level detail beyond that, matching the baseline for a fully documented schema.

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 names a specific action ('Build a working web app'), the input source ('from a prompt'), and the key output ('returns a buildId'). It distinguishes itself from siblings like get_build_status by explicitly pointing to that tool for polling progress.

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?

It gives clear operational context: this is the asynchronous, credit-costing first step for creating an app, with get_build_status as the follow-up. It stops short of naming explicit when-not-to-use conditions or alternative build approaches, so it does not earn a 5.

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