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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'never runs one' and the interpretive guard 'each is an observation, not a rate,' which provides meaningful context beyond the annotations without contradicting 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?

Three short sentences carry purpose, ordering, safety, and interpretation with no filler. Each clause earns its place, and the most distinguishing information is front-loaded.

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 read-only annotations, three optional parameters, and no output schema, the description covers what is returned (already-run experiments, newest first), the safety profile, and a key interpretation caveat. The main gaps are the lack of explicit filter semantics and output shape, but they are minor for a simple list tool.

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%, and the description does not explain limit, idea_id, or experiment_id. The parameter names are somewhat self-explanatory, but 'with scoped evidence' only vaguely hints at filtering, leaving the agent to guess how the parameters shape the result.

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 specific resource (growth content experiments), states they are already run, and adds ordering ('newest first') and a semantic qualifier ('each is an observation, not a rate'). It does not explicitly distinguish from sibling tools by name, but the purpose is unambiguous.

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 this tool is for retrieving historical experiments and explicitly notes it never runs one, which helps route an agent away from using it for execution. However, it does not name alternatives or state when to prefer this over siblings like get_scoreboard or get_outcomes.

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