PRD Review

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

The description explicitly discloses that this is a write operation ('A write: each call re-runs the review and persists it as a new version'), which complements the annotations (readOnlyHint: false) and adds context about versioning and side effects. It also reveals 'One small LLM call' for cost/performance and notes the draft-only scope, going well beyond the structured annotations.

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?

The description is dense but every clause earns its place: it covers purpose, criteria, output format, side effects, ID resolution, cost, and recommended timing. It is front-loaded with the core purpose and uses punctuation to separate concerns. No filler or repetition.

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 there is no output schema, the description thoroughly explains the return payload (structured findings with section, severity, concrete suggested fix, verbatim quote, plus a score). It also covers prerequisites (target_id resolution), side effects (persists new version), and use case ('before sending a draft for sign-off'). Complete for a tool of this complexity.

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%, so the baseline is 3. The description adds value by explaining how to resolve target_id (via pm_meta or list_* tools) and by clarifying the target_type semantics (feature = spec, experiment = plan, page = doc/PRD). This enriches the bare schema without redundancy.

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 this is an 'Agent-as-critic' review tool for DRAFT artifacts, specifying the artifact types (feature spec, experiment plan, page), the review criteria (baseline PM bar), and the structured output (findings plus 0-100 score). It distinguishes itself from sibling tools like get_page or update_page by emphasizing it checks and critiques rather than reads or edits.

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 provides clear usage context: 'use it before sending a draft for sign-off' and instructs to 'Resolve target_id first' via specific sibling tools (pm_meta, list_features, list_experiments, list_pages). It does not explicitly say when not to use it or name direct alternatives, but the context is strong and actionable.

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