design_review

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the enforced max-round limit, persistence with deltas to a specific file, the computed metrics, and the refusal behavior for round 4. This exceeds typical transparency expectations.

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 concise and front-loaded, starting with the core purpose in the first sentence. Every sentence contributes essential context: enforcement, computation, persistence, return value, and iterative usage. No word is wasted.

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?

Despite lacking an output schema, the description fully explains the return value (a structured rubric with six specific criteria), the persistence behavior, the round limit, and the recommended user action on refusal. This makes the tool's operation completely understood.

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?

The single parameter 'notes' is already fully described in the schema as 'What this round focused on / what changed since the last round'. The description adds no further parameter-specific detail beyond the schema, so the baseline of 3 applies due to 100% schema 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 identifies the tool as an iterative design-review round with specific actions: computing validation and rationale coverage, persisting to reviews.json, and returning a structured rubric. It distinguishes itself from siblings by naming the enforcement limit (max 3) and the rubric criteria, making its function unambiguous.

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?

It explicitly describes the iterative workflow: 'Address the rubric, improve the design, then call again' and instructs that round 4 should be refused and results presented to the user. This is strong contextual guidance, though it does not explicitly compare to alternative tools like screen_critique or design_audit.

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