Program Creation Evals

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

Annotations already indicate read-only, idempotent, and non-destructive behavior, so the description only needs to add extra behavioral context. It does so by specifying that the tool produces 'one-shot' evaluation prompts and acceptance checks, and by listing the four focus areas, which goes beyond mere annotation repetition.

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 entire description is one front-loaded sentence with no filler. It states the verb, resource, purpose, and key scope areas in a compact list, so every part earns its place.

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?

Output schema and annotations cover return values and safety behavior, and both parameters are optional with defaults, so an agent can invoke the tool minimally. However, with no schema descriptions for parameters, the description leaves programType semantics and the effect of includeOneShotPrompts unexplained, creating a notable completeness gap.

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%, so the description carries the burden of explaining the two parameters, but it does not mention programType or define what includeOneShotPrompts controls. Only the word 'one-shot' weakly hints at one parameter, and 'program-creation' weakly hints at the other; this is insufficient compensation for a low-coverage schema.

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 opens with a specific action, 'Generate one-shot GrowSurf program-creation eval prompts and acceptance checks', naming both the deliverable and its purpose. The colon-delimited list of coverage areas further distinguishes it from the many operational sibling tools, making its unique role clear.

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 phrase 'for agent steering' implies the intended context, and the content areas suggest evaluation scenarios. However, there is no explicit when-to-use/when-not-to-use guidance or mention of alternatives, leaving the selection logic mostly to inference.

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