athena_prompt_experiment

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that this is a persisting (write) operation and adds a validation rule regarding observed/verdict, but it does not mention idempotency, duplicate behavior, whether candidate_ref must already exist, required permissions, or what the tool returns.

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 dense sentence that front-loads the operation and includes a meaningful constraint. Every word earns its place, and there is no redundant filler.

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?

For a 7-parameter persist operation with nested objects, no output schema, and no annotations, this description is too sparse. It does not explain return behavior, required relationships between parameters, the meaning of 'baseline/candidate', or the tool's place in the prompt experiment workflow relative to sibling tools, making it incomplete for reliable invocation.

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 must compensate for explaining the 7 parameters. It only clarifies the relationship between observed and verdict ('observed PASS' requires execution), leaving candidate_ref, expected_git_head, observations, evidence_refs, and actor without semantic explanation beyond their names and types.

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 uses a specific verb ('Persist') and a specific resource ('baseline/candidate prompt experiment record'), clearly indicating it saves a prompt experiment record. The constraint about unexecuted designs adds scope and distinguishes it from sibling prompt-lifecycle tools like athena_prompt_propose or athena_prompt_activate, which focus on other stages.

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 when recording the outcome of a prompt experiment, and it explicitly warns that unexecuted designs cannot be recorded as observed PASS. However, it does not name alternatives or explain when to choose this tool over related experiment/prompt tools, leaving the guidance only implicit beyond the validity constraint.

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