Create a versioned prompt candidate

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

Annotations indicate non-read-only and non-destructive. The description adds the constraint that prompt must contain '${output}', which is useful. However, it does not disclose versioning behavior, whether duplicates are allowed, or any error states. No contradictions.

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?

Two concise sentences front-load the purpose and critical constraint. Every word contributes value. However, the structure could be improved by separating the constraint into a note.

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 4 parameters, a nested object, and no output schema, the description is adequate but incomplete. It lacks validation rules, behavior on duplicate 'name', return value, or prerequisites. The constraint on prompt is helpful, but more detail on settings defaults and allowed values is needed.

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 coverage is 0%, so description must compensate. It mentions 'prompt template, model, and inference settings' but does not explain individual properties like 'name', 'settings.minP', or their roles. Only the prompt constraint is clarified.

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 stores an immutable prompt candidate with specific components (template, model, settings) for evaluation. It distinguishes from siblings like 'freeze_prompt_candidate' and 'promote_candidate_to_lm_studio' by focusing on the creation/storage step.

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 mentions 'for evaluation' but provides no explicit guidance on when to use this tool versus alternatives like 'freeze_prompt_candidate' or 'run_development_eval'. It lacks when-not-to-use or exclusion criteria.

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