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

Well beyond the annotations (which already cover read-only/idempotent/no-destroy): it discloses that test sends are excluded so zeros are correct, that empty top_links means no clicks while null means unreadable, that steps[].Index is 0-based versus the 1-based Step on links, that daily rows are UTC, the 180-day retention cap, and the split module gating with instructions to read back the named module on a 403 instead of guessing. This is exactly the non-obvious behavior an agent cannot infer.

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?

Purpose is front-loaded and nearly every sentence carries a distinct semantic trap, which justifies the unusual length. There is some redundancy — the valid window set and the 180-day rationale are restated, and the no-create-endpoint passage is tangential to invoking a fetch — so it is dense but not maximally tight.

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?

There is no output schema, so the description carries the whole burden of return semantics and does so comprehensively: top_links content and cap, empty-vs-null distinction, PascalCase keys, dual numbering schemes, test-send exclusion, and the retention-bounded window. An agent can interpret and report this payload correctly without further information.

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 real meaning: the default of 30, that values outside the set are rejected, why 180 is the ceiling (row retention), and the UTC-day caveat that affects how the window should be described. drip_token itself gets no extra explanation, so it is not a full 5.

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 opening names a specific resource plus its exact payload facets: 'Message statistics of a drip campaign: per step, in total, day by day, and the links people clicked.' That scope distinguishes it in practice from get_drip (configuration), fetch_drips/fetch_drip_enrollments (lists) and fetch_campaign_report (campaigns). No verb is stated outright, but the data scope is precise enough that an agent knows exactly what it retrieves.

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?

Sets hard usage bounds: only 7/30/90/180 windows are valid, never offer a longer one, quote server-computed rates as given, state which window and which day you are reporting, and never propose or invent a create/edit tool because those writes live only in the Sweeppea app. It lacks an explicit pointer to a sibling (e.g. fetch_drip_enrollments for recipients), so it stops short of a 5.

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