Turnkey Specification from Description

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

Annotations provide minimal behavioral info (no readOnly, destructive, idempotent hints). The description adds context: it generates files (spec_dir), can overwrite (force), supports iterative refinement via clarification_responses, and automatically extracts requirements. However, it does not detail behavior when force=false or output specifics.

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?

Three sentences: first states core action, second lists key features, third sells value. No filler, front-loaded with the most important information. Perfectly concise.

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 no output schema and minimal annotations, the description covers the main workflow (generation, refinement) and side effects (file overwrite). It lacks exact output format or file naming, but is sufficient for understanding tool behavior. Slight gap in output details.

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% with descriptions for each parameter, giving baseline 3. The description adds process context: how description is processed (extracts, classifies, generates criteria) and how clarification_responses enables refinement. This extra meaning justifies a 4.

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 generates a complete EARS specification from natural language, enumerates specific outputs (requirements, patterns, criteria, clarifications), and distinguishes from siblings by emphasizing speed ('fastest way'). The verb 'Generates' and resource 'EARS specification' are precise.

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 implies usage for rapid spec creation ('fastest way to go from idea to spec') but does not explicitly state when to avoid or compare to siblings like sdd_write_spec. Usage guidance is implied but limited.

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