generate_prd

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

No annotations are provided, so the description carries the full behavioral burden and it does not disclose that this writes a file to disk, whether it overwrites an existing PRD.md, path-resolution defaults, or what happens on failure. The single clue about the artifact is the "(PRD.md)" filename suffix, which is thin for a write operation with zero annotation coverage.

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?

A single densely-packed sentence with the artifact type and its defining characteristics front-loaded. No wasted words, though the parenthetical acronym stacking is slightly heavy.

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?

For a 10-parameter generator with no output schema and no annotations, the description conveys what artifact is produced and its key sections, which is useful. It is not complete enough regarding file-write behavior, path resolution, or the non-core parameters (detail, templatePreset) that shape output size and structure.

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%, so the description must compensate but only partly does: it explains the conceptual outputs (MoSCoW priority, out-of-scope boundaries, Gherkin scenarios) that map to keyFeatures.priority, outOfScope, and gherkinScenarios. Parameters like detail, templatePreset, targetAudience, problemStatement, and tagline are not addressed at all by the description.

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 a specific verb+resource ("Generates an anti-hallucination Product Requirements Document (PRD.md)") and names the distinguishing content (MoSCoW, scope boundaries, Gherkin criteria), which differentiates it from siblings like generate_srs or generate_sdd. It stops short of explicitly naming the alternative generator tools, keeping it at 4.

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 gives no when-to-use, when-not, or alternative-routing guidance; nothing tells the agent why to pick this over generate_full_blueprint or generate_srs. The only usage-like instruction (asking where the project is) lives in the schema's outputPath field, not in the description.

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