draft_file

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

Annotations are absent, so description carries full burden. It successfully discloses the non-destructive/read-only nature ('Does not write files'). However, it omits what happens to the generated draft (return value format, persistence, size limits) and how 'local patterns' are weighted.

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 zero waste: first states purpose and mechanism, second states critical safety constraint. Every word earns its place and the safety warning is appropriately front-loaded.

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?

Given 100% schema coverage and simple 4-parameter structure, the description is minimally adequate. However, it fails to compensate for the missing output schema by describing what the tool returns (the draft content) or how it should be handled.

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%, establishing baseline 3. Description references 'intent' and 'local patterns' which loosely map to the intent and similar_files parameters, but adds no syntax guidance, format examples, or constraints beyond the schema definitions.

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 specific action (generate), resource (file draft), and inputs (intent, local patterns). The 'Does not write files' clause distinguishes it from mutation siblings like suggest_edit or find_and_fix. Could reach 5 with explicit comparison to code_helper or suggest_edit.

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?

Provides clear negative constraint ('Does not write files') implying when NOT to use it, but lacks explicit positive guidance on when to prefer this over similar generation tools like code_helper or generate_docs.

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