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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered. The description goes further by disclosing the returned aggregates (average, csat, responseRate, count per score), the per-platform breakdown, the newest-first ordering, and pagination via 'before = the previous answer's next' — genuinely useful behavior beyond annotations. It stops short of noting rate limits, default windowing behavior for days, or whether the list is complete across pages.

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 purpose and the crucial mobile caveat, then returns, then scoping, then pagination — a logical progression. It is dense and long-ish, and the returns sentence is heavily compressed, but no sentence is filler.

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 contract, and it does: aggregate metrics, per-platform totals, and the per-rating records with customer, comment, and closer. Combined with the readOnly annotation and full schema coverage, an agent has everything needed to call and interpret this correctly.

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 100%, so all five parameters are already documented; the baseline is 3. The description does add meaning the schema does not spell out: 'without appId on an all-apps key it covers every app' clarifies the omission semantics, and 'before = the previous answer's next' restates the cursor contract. It says nothing extra about rated or days 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?

Opens with a specific verb+resource ('Satisfaction ratings from web chats') and immediately scopes the data domain: 1-5 CSAT from the chat-closing widget, with mobile apps explicitly excluded. No sibling tool in the list covers ratings, and the description makes that uniqueness unmistakable.

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 implied rather than stated: the reader can infer this is the tool for CSAT reporting, and the mobile-app caveat prevents a wrong attempt (no ratings there). However, it never says when to prefer it over e.g. coming_up or list_subscribers, nor mentions any preconditions such as needing list_apps to resolve appId — that hint lives only in the schema.

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