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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds useful behavior beyond that: newest-first ordering, the assignment-source taxonomy, and the enrollment flag. It doesn't cover pagination behavior or response size limits, which the schema's defaults only partly imply.

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?

The description is a single front-loaded paragraph that opens with the resource and scope before the filters and workflow example. The dense em-dash phrasing packs in a lot, but every sentence, including the skill prerequisite, carries operational value.

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 9-parameter, non-mutating list tool with no output schema, the description does the heavy lifting on return shape and filtering and adds a workflow pointer. Minor gaps remain around pagination semantics and the required experimentId parameter.

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?

With 67% schema coverage the baseline is 3, but the description adds practical meaning: search matches on unit id, the filters are group/status/source, and the source values are explained as how a unit got into its group. The required experimentId and page/pageSize parameters remain undescribed in both schema and description.

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 names a specific verb and resource (list the units assigned to an experiment) and enumerates the returned fields: current group, assignment source (weightedHash/roundRobin/manual), and enrollment state. This is clearly distinguishable from siblings such as get_cohort_members or get_experiment_results.

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?

It gives concrete when-to-use guidance ('to check which group a specific player is in before changing it with assign_experiment_unit') and a prerequisite (load the understand-experiments skill first). It doesn't explicitly state when not to use it, e.g. that aggregate results belong to get_experiment_results.

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