Rank Test Candidates

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

Annotations already establish that this is a read-only, idempotent, non-destructive operation. The description adds meaningful context by specifying the ranking criteria (risk reduction and maintenance cost), which goes beyond what annotations convey. It does not contradict any annotation, and there are no hidden side effects implied.

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 a single, clear sentence that front-loads the verb and resource. It contains no filler, repetition, or unnecessary details. Every word contributes to understanding the tool's purpose.

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 tool has one parameter and no output schema, so the description should convey what the result looks like. It states that ranking is done, but does not specify the output format (e.g., sorted list, scores attached, ordering direction). This leaves some ambiguity about the return value for an agent invoking the tool.

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 schema fully describes the single 'audit' parameter as 'An audit/v1 artifact' with 100% coverage. The description refers to 'testable audit targets' but does not add any new semantics for the parameter itself, such as format requirements or how the audit should be structured. Baseline of 3 is appropriate given complete 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 states the action (rank), the resource (testable audit targets), and the specific criteria (risk reduction and maintenance cost). This distinguishes it from the sibling tool rank_project_candidates, which ranks projects rather than test candidates.

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 context: when you have an audit artifact and want to rank test candidates, use this. It does not explicitly list exclusions or mention alternatives like rank_project_candidates, but the scope is evident from the wording. This meets the 'clear context, no exclusions' level.

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