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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. Beyond that the description adds the plan requirement and the underlying endpoint (GET /api/v2/analytics/experiments), plus a warning that results are descriptive only and report n per group — useful context, though nothing on unlabelled posts, sparse groups, or rate limits.

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?

Two tight sentences with the core operation front-loaded first, then limits and prerequisites. The bracketed "[read-only]" is mildly redundant with readOnlyHint but serves as a fast scan cue; no sentence is wasteful.

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 correctly fills that gap by stating the return shape (medians with n per group at the 48h/7d snapshots). Given five optional parameters at 40% description coverage, it is close to complete but doesn't clarify the "latest" window or the "include":"posts" option.

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 only 40%, so the description must carry weight; it does explain the most important parameter (`key`) with a worked example showing how label values become comparison groups. The remaining parameters (metric, window, brandId, include) are left entirely to enum values and inline schema text, with no added meaning about defaults or interaction between `key` and `window`.

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?

"Splits every labelled post by the values of one label key ... and reports medians with n per group" gives a specific verb, resource, and output shape, and the concrete "cut:opus vs cut:raw" example removes ambiguity about what a label key split means. It differentiates itself from statistical comparison tools via "Descriptive, not a significance test," though no sibling is named.

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?

The description supplies a real exclusion ("not a significance test") and a prerequisite ("Pro plan or higher"), which tells an agent both the analytical limit and an access gate. It stops short of naming an alternative tool for when a true significance test or per-post comparison is wanted.

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