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

Annotations already declare the safe read profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context beyond them: results are computed over actual participants (data semantics, not raw config) and legacy tests are supported.

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 tight sentences with the core purpose front-loaded and no filler. Slightly dense/telegraphic in the second half ('Legacy tests also supported'), but every sentence carries information.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile. For a read-only tool at this complexity, the remaining gap is only the undocumented runId/testId parameters.

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 only 33% (runId and testId are undocumented). The description partially compensates by telling the agent that block/run IDs come from list_test_blocks and that omission uses defaults, but it adds nothing for the required testId beyond the schema.

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 verb (Read) and resource (audience targeting and demographic breakdowns) and scopes it to 'the actual participants in this test', which is a meaningful distinction from a configured-audience lookup. It explicitly separates itself from get_tester, though it stays silent on list_audiences/create_audience neighbors.

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?

Explicitly routes the one-participant case to get_tester and tells the agent to source block/run IDs from list_test_blocks, plus notes omission behavior and legacy support. It gives clear when-to-use context but no when-not or full alternative map (e.g. vs list_audiences).

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