Run prompt candidate on development set

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

The annotations (readOnlyHint=false, destructiveHint=false) are minimal, so the description carries the burden of behavioral disclosure. It adds important context: that the evaluation is sequential, metrics are recorded, and LM Studio's prior model state is restored afterward. This informs the agent about side effects and cleanup, going beyond 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 extremely concise, consisting of two sentences. The first sentence efficiently states purpose and captured metrics; the second adds a critical behavioral note. No unnecessary words, making it easy to parse.

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 the tool's simplicity (2 parameters, no output schema), the description covers the core action and a behavioral note. However, it does not describe the return value or output format, which is important since there is no output schema. It also fails to differentiate between required and optional parameters.

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 does not explain the parameters (datasetId, candidateId). The description only mentions evaluating a candidate but does not clarify that candidateId is required or what datasetId affects. This lack of parameter documentation creates a significant gap for the agent.

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 tool evaluates a prompt candidate against development examples and records specific metrics (exact-match and latency). The verb 'evaluates' and the resource 'candidate against development examples' are explicit. It is easily distinguished from the sibling tool 'run_holdout_eval' which evaluates on a holdout set.

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 implies usage for evaluating on a development set and notes that prior model state is restored afterward, which hints at a non-permanent operation. However, it does not explicitly state when to use this tool over alternatives like 'run_holdout_eval' or provide context on prerequisites or conditions for use.

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