research.generate_specs

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

No annotations are provided, so description carries full burden. It discloses that writing requires approved=true and writes through Memoire registry. However, it does not describe what happens to existing specs (overwrite vs append), error behavior, or authorization requirements beyond the boolean flag. Adequate but not detailed.

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 plus a bulleted list of spec types. Every sentence adds value: first states core purpose, second gives prerequisites and requirement, third lists outputs. No redundancy, front-loaded with key action.

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?

No output schema, so description needs to explain return values; it lists spec types written. However, it omits information on error states, idempotency, or how multiple writes are handled. With 5 parameters and no annotations, it is somewhat complete but could cover more behavioral 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 40% (only research and approved described). Description adds context for approved (must be true to write) but does not explain intent, hypothesis, or runId. The research parameter is partially explained as 'optional ResearchStore JSON string'. Overall, description adds some value beyond schema but does not fully compensate for low coverage.

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 research-backed Atomic Design specs from ResearchStore V2. It lists the specific spec types (DesignSpec, IASpec, etc.) and distinguishes itself from sibling tools like research.design_package (preview) and create_spec (generic). The verb 'write' and resource 'specs' are specific.

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 prerequisite: call research.design_package first. Requires approved=true to execute. Provides clear context for when to use (after preview) but does not mention when not to use or alternatives beyond the prerequisite.

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