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

Annotations already cover readOnly/destructive/closed-world, and the description adds genuinely new behavioral context: result ordering (newest first) and a semantic caveat that each entry is 'an observation, not a rate,' which affects how an agent should interpret and report the data. It does not describe pagination or result size beyond the limit param.

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?

Three short clauses, front-loaded with the resource and ordering constraint, with no filler. The phrases 'scoped evidence' and 'observation, not a rate' are terse to the point of being cryptic, costing a little clarity.

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 read-only list tool with no output schema the description covers behavior and interpretation reasonably well, but it leaves all three input parameters unexplained despite 0% schema coverage, which is a meaningful gap for an agent deciding how to call it.

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% for all three parameters (limit, idea_id, experiment_id), so the description carries the full burden — yet it never mentions any of them. 'Scoped evidence' vaguely gestures at scoping but does not explain that results can be narrowed by idea or single experiment, or what limit does.

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?

States a specific resource (growth content experiments already run) and scope (newest first, with scoped evidence), which is enough for an agent to distinguish it from the many other get_* siblings. It lacks an explicit verb in the description itself, relying on the title 'View experiments' for the action.

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 a retrieval use case for past experiments and rules out one misuse ('never runs one'), but gives no conditions for choosing it over alternatives or when to prefer filtering by idea vs experiment. Usage is inferable rather than stated.

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