Recommend Study Run

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

The description goes beyond annotations by clarifying that the write operation only records a recommendation and does not itself accept or promote, which is a non-obvious behavioral trait. Annotations already flag readOnly=false, idempotent=false, and destructive=false, and the description does not contradict them.

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 short sentences deliver the core action and the key exclusion with no filler. The most decision-relevant constraint—'does not accept or promote'—is clearly stated after the action.

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?

With an output schema present and annotations covering side-effect flags, the tool is not wildly under-specified: an agent can tell it records a recommendation for a study run with evidence. However, because the parameters are undocumented, the workflow context—such as which evaluation/run IDs are valid and how this relates to adoption—is incomplete.

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%, and the description only loosely hints that 'reason' should carry evidence. The three identifier parameters (study_id, run_id, evaluation_id) and their relationships are left entirely to name inference, so the description does not sufficiently compensate for the lack of schema property descriptions.

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 identifies a concrete action—record a recommendation—with the object 'with evidence,' and explicitly marks what the tool does not do (accept or promote a model), which separates it from adoption/promotion siblings. It relies on the title for the 'study run' context, but the verb-resource pairing is specific enough.

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 statement 'analyst acceptance happens in the frontend' gives an explicit when-not: this tool is for recording, not for accepting or promoting. It does not name a sibling alternative such as adopt_model_into_study, so an agent must infer which tool to use instead, but the boundary is clear.

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