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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context with 'Nobody is identified', telling the agent the result is aggregate and cannot be tied to individual users or sessions — a constraint that affects how the output may be used. It stops short of describing return shape or whether per-tag counts are exclusive.

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?

A single compact sentence puts the primary quantity first, then the breakdown dimension, then the key caveat. No filler, no restating of the title, and the most decision-relevant information is front-loaded.

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 four-parameter read-only aggregate tool with a fully documented schema and full annotation coverage, the description covers what is counted, the breakdown dimension, and the anonymity constraint. Minor gaps remain around the exact result shape and edge cases (empty period, disabled recordings), but nothing essential to selecting or invoking the tool is missing.

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%, and the period/from/to/website semantics (timezone, dashboard-style ranges, custom pairing, website id or domain) are fully documented in the schema. The description adds nothing about parameters, so the baseline 3 applies.

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 description states a specific verb-and-resource pair: it counts recorded sessions in a period and returns per-problem-tag counts (rage clicks, errors, slow pages). That is distinguishable from list-style siblings like list_websites or get_pages, though it never names a sibling (e.g. get_overview or get_insights) that would cover similar ground.

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 only implied by the interrogative framing — an agent can infer it answers 'how much recording activity and what problems occurred'. There is no explicit when-to-use, when-not-to-use, or pointer to alternative tools, and no prerequisite (such as recordings being enabled) is stated.

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