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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real context beyond them: results are conditional on status, with full Bayesian detail only for running or finished experiments. It omits volume/ordering concerns for a list-everything tool, which keeps it from a 5.

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?

A single front-loaded sentence with no filler; the conditional qualifier ('for running or finished ones') is placed before the payload list so the reader knows the results are partial for other statuses.

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 no output schema, the description carries the return-value burden and does name the key fields (exposures, conversions, probability-best variant). Gaps remain: no mention of scope boundaries (all experiments in the account? by surface?), ordering, or whether the call is expensive for large accounts.

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?

The tool takes zero parameters, so there is no parameter semantics to document; the baseline of 4 applies. The description correctly spends no words on inputs and instead covers scope of output.

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 (every experiment) and what comes back with it (status plus Bayesian results for running/finished ones). The verb is only implied by the name, and it never explicitly names get_experiment as the single-item alternative, so sibling differentiation is left to inference.

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?

Usage is only implied: the 'every experiment' framing suggests bulk retrieval versus the singular get_experiment sibling, but there is no explicit when-to-use statement, no exclusions (drafts? archived?), and no guidance on choosing between this and get_experiment.

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