Propose rule evolution from fix

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

With no annotations, the description fully discloses key behavioral traits: it writes to a PENDING queue, does not modify .cursor/rules files, and requires human APPROVAL before application. This gives the agent a clear safety profile and workflow understanding.

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?

Four sentences, each earning its place: purpose, write target, approval requirement, and governance summary. Information is front-loaded and there's zero waste.

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?

The description covers the core behavior and workflow adequately. It doesn't explain return values or file naming, but given no output schema and 100% parameter coverage, the essential context is present. A minor gap is not specifying what the tool returns on success or whether it errors on duplicate proposals.

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 description coverage is 100%, so parameters are already well-documented. The description does not add parameter-specific details, but it provides useful workflow context (e.g., 'learned pattern', 'PENDING queue') that reinforces the purpose. Baseline 3 is appropriate.

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 states exactly what the tool does: propose a learned pattern as a new rule entry after a test passes following an automated fix. It distinguishes from siblings by emphasizing it writes to a PENDING queue and does NOT modify rules files directly, clarifying its governance role.

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 gives a clear trigger condition ('after a test passes following an automated fix') and contrasts with direct file modification. It doesn't explicitly name alternative tools like validate_and_apply_fix, but the governance framing makes when to use it unambiguous.

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