fit_check_apply

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

No annotations are provided, so the description must fully disclose behavioral traits. It implies mutation by 'write rejected sidecar' but does not confirm if the operation is destructive, reversible, or requires authorization. The term 'sidecar' is undefined. Lacks transparency about side effects.

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 extremely short (one sentence) and upfront about the action. However, it is too terse and sacrifices clarity for brevity. Every word earns its place but fails to provide sufficient detail.

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 the existence of an output schema, the description is incomplete. It fails to explain the core workflow, parameter roles, or the nature of the 'rejected sidecar'. The tool has 4 parameters including nested objects, yet the description offers no guidance.

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 0% and the description adds no meaning to the parameters. Parameters like 'cluster_slug', 'candidates', 'scores', and 'threshold' are not explained. The agent cannot infer how to format the input or what 'threshold' controls.

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 the verb 'consume', 'filter', 'write' and resources 'AI scores', 'candidates', 'rejected sidecar'. It indicates the tool processes scores to filter candidates and produces a sidecar. However, 'rejected sidecar' is ambiguous and could be clearer. It distinguishes from sibling tools like fit_check_audit and fit_check_prompt.

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?

No guidance on when to use this tool vs alternatives. The description does not specify prerequisites, when not to use, or mention sibling tools for comparison. The agent has no context to decide between fit_check_apply and fit_check_audit.

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