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

Annotations cover the safe-read profile, and the description goes well beyond by disclosing the large-read guardrail (>10000 profiles returns counts and credits until confirmLargeRead is true), the API call budget (1 per 200 profiles, 1 per 200 clients, at most 1001), and the important caveat that startedInRange misses memberships that have since ended. These are exactly the operational facts an agent needs before invoking.

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 purpose and outputs, then alternatives, then cost, in a sensible order; there is essentially no filler. It is a single dense paragraph, so the alternative routing and the call-budget sentence are somewhat buried rather than visually separated.

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 eight optional parameters, no output schema, and an open-world read, the description supplies the output categories, the large-read behavior, and the temporal semantics that the schema alone cannot. The exact return shape (e.g. field names beyond byMembership and startedInRange) is only partly implied, which keeps it short of perfect.

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, but the description adds interpretive meaning the schema does not: the range/startDate/endDate window applies only to startedInRange while all other counts are as-of-today, and startedInRange is framed as a substitute for 'new members' with a known blind spot. It does not add much on top/top folding or membershipIds beyond the schema wording.

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 with scope: 'Active memberships at one site today', then enumerates the four outputs (member count, count per membership, unheld memberships, startedInRange). This is clearly distinguishable from get_memberships (name lookup) and the other summary siblings.

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?

Names three alternatives with the condition that selects each: new_clients_summary for new clients/first visits, clients_at_risk for non-renewal, sales_summary for revenue. It also states an exclusion up front ('A snapshot of today, with no comparison or past date'), so the agent knows not to reach for it for trend questions.

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