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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=true, idempotent=false), and the description adds substantial non-obvious behavior: the two-call WAIT/jobId polling protocol, the one-to-two-minute runtime, that every build is attributed to a real customer, and that FAIL returns the tail of the failing step output.

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?

Front-loaded with the core action and protocol, then prerequisites and failure handling. Dense and mostly waste-free, though the final FAIL-handling sentences could be tightened slightly.

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 complex asynchronous two-phase tool with no output schema, the description covers the call protocol, timing, required provenance, failure output, and the retry loop — everything an agent needs to invoke and recover correctly.

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, but the description adds real meaning beyond the schema: `files` must be the FULL project (not just changed files), and `projectid` must belong to a purchased project. It also explains the jobId polling pattern, though it does not elaborate on envVariables beyond what the schema says.

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 and resource — runs a real `npm install && npm run build` on an isolated GitHub Actions runner and reports build success. It is clearly distinguishable from siblings like get_scaffold (retrieval) and purchase_scaffold (acquisition).

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?

Explicitly says to use this after editing a get_scaffold result and before handing it to the user, and that it requires a projectid from a prior purchase_scaffold. It also names the alternative artifacts (get_scaffold, purchase_scaffold, get_component's envVariables) that feed into it.

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