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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds useful behavior beyond them: default ordering by lastTrackedAt and the hard cap of 100 groups returned. It stops short of spelling out pagination, though the offset/limit schema largely covers that.

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?

Front-loaded with the core purpose, followed by ordering, filters, a cross-reference, and a return cap, all in three sentences with no filler. The lead sentence is long and parenthetical-heavy, which slightly taxes readability but every clause 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?

For a read-only list tool with no output schema, the description supplies what an agent needs: what is listed, default ordering, filter options, the return-size cap, and the sibling to use for member details. Annotations carry the safety profile, leaving no material gap.

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 coverage is 100%, so the baseline is 3. The description goes a step further by tying parameters to intent: default sort is recency, the identity filter specifically lists the groups an identity belongs to, and the type filter uses the customer's own naming. That interpretation aid is value beyond the schema's field-level text.

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 and resource and immediately disambiguates what 'groups' means here (customer-reported collectives, 'not clusters Dregs detected') and what is returned (type plus member identity count). An agent can distinguish it from get_group and list_identities without opening any schema.

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?

Gives explicit alternatives: to list a group's members, call list_identities with its id and type. It also names the available filter modes (type, free-text term, identity id) and what each is for, so the agent knows which to reach for.

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