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

With no annotations at all, the description carries the full behavioral burden and delivers: the async two-phase protocol (start with files → WAIT + jobId → poll with jobId → OK/FAIL with compiler error), the 'real' build side effect, the full-project requirement, cost ('Free, no API key needed'), and expected latency ('one to two minutes'). This is exactly the kind of behavior an agent cannot infer from the schema.

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?

Roughly 130 words covering purpose, cost, usage timing, the async handshake, failure output, and latency — every sentence earns its place. The core action is front-loaded and the complex two-phase protocol is explained in a single flowing passage without 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 a 3-parameter async tool with no output schema and no annotations, the description covers the essential contract: start/poll invocation pattern, status values (WAIT/OK/FAIL), and failure detail. Minor gaps remain — the full response shape beyond status is unspecified and jobId's validity/error behavior is not addressed — but the core calling protocol is complete.

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 100%, so the baseline is 3; the description adds real value on top by explaining the lifecycle connecting the parameters: files must be the entire project including edits, jobId originates from a prior WAIT response and drives polling, and envVariables maps to generate_scaffold's output. This goes beyond the schema's per-parameter text.

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 opens with a specific verb-plus-resource statement: 'Runs a real `npm install && npm run build` against the given files and reports whether the project builds.' This clearly distinguishes verify_scaffold from its siblings, especially generate_scaffold, and explicitly anchors it in the generation workflow.

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 description gives explicit workflow context: 'Use it after editing a `generate_scaffold` result... before handing the project to the user.' This tells an agent exactly when the tool applies. It stops short of naming when-not-to-use it or contrasting it with a sibling like check_component_updates, so it does not fully earn a 5.

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