draft_design_doc

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

With no annotations, the description carries full burden. It discloses that the tool returns a short digest and the orchestrator reads and edits the file, plus the writing to out_path. It could mention more about error handling or permissions, but provides reasonable transparency.

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?

Description is structured with paragraphs and an Args list. Front-loaded with the core action. Every sentence adds value, though could be slightly more concise without losing detail.

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 tool complexity (5 params, output schema exists), the description covers return behavior, pipeline context, and parameter roles. It adequately informs an AI agent, though more details on error cases or expected output format would improve completeness.

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 0%, so description compensates by listing parameters with explanations (e.g., 'batch_ids: review_fanout / research_fanout batch IDs'). Adds meaning beyond the bare schema, though some parameters could be more detailed.

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's purpose: drafting a structured design document from on-disk batches. It uses specific verbs ('draft', 'reads') and distinguishes itself from sibling tools as the synthesis step of the Architect pipeline.

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 explains the tool's role as the synthesis step, requiring review and research batch dirs plus a verified brief. It implies usage after prior steps but does not explicitly state when not to use or list alternatives.

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