generate_spec

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

The description discloses key behaviors: it writes multiple files to a directory, and optionally sends page screenshots and source code to Groq for vision-assisted classification. It notes this is off by default and that nothing changes if unset. No contradicting annotations. However, it does not mention whether existing files are overwritten.

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 dense but well-structured: main purpose first, then precondition, then optional configuration with explanation. No redundant information; every sentence serves a purpose. Appropriately sized given the tool's conditional behavior.

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?

The description covers preconditions, output location, and optional behavior. However, with no output schema, it does not describe what the tool returns (e.g., success message, list of created files). This gap reduces completeness for an agent that needs to understand the tool's response.

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% for the single parameter repoPath, providing a detailed description of its role. The tool description adds value by listing the specific files written, which is not in the schema description. Thus it surpasses the baseline of 3.

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 clearly states the tool writes specific files (CLAUDE.md, .claude/, spec/, tests/, kickoff-prompt.txt) to a <repo>-rebuild/ directory. It distinguishes itself from siblings by specifying it generates specs and tests after ingestion, and its call precondition (case queue empty) differentiates it from e.g., ingest_repo or crawl_site.

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 states the precondition 'Only callable once the case queue is empty' and provides detailed guidance for Next.js apps with optional vision classification configuration, including how to obtain and set the required API key. This gives clear when-to-use and how-to-use instructions.

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