generate_spec

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

No annotations are provided, so the description must carry the full behavioral burden, and it does: it states the file-writing side effect, the queue precondition, the optional behavior of the vision classification (sending data to Groq), and the explicit statement that this tool never logs in or handles credentials itself. It also notes the file is gitignored.

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?

The description is long but every sentence carries essential information: the deliverable, the precondition, and two optional behaviors with explicit 'if unset' fallbacks. It is front-loaded with the core action. Slightly dense, but nothing is filler.

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 no output schema and two parameters, the description covers prerequisites, side effects, optional features, credential handling, and environment-variable behavior. Nothing an agent needs to decide whether and how to call this tool 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 baseline is 3. The description adds context about the auth parameter's purpose and behavior, and explains the environment variables, but these are not schema parameters. It doesn't substantially extend the meaning of the two parameters beyond what the schema already provides.

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 states a specific verb ('Write') and lists exactly which files are produced (CLAUDE.md, .claude/, spec/, tests/, and <repo>-rebuild/). This clearly distinguishes it from siblings like ingest_repo or crawl_site, which have different targets and actions.

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 provides an explicit precondition ('Only callable once the case queue is empty') and detailed optional triggers (vision classification env vars, auth storage state) with when-to-use guidance. It doesn't explicitly contrast with sibling tools, but the queue-empty condition and the unique output files make the intended context clear.

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