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

Annotations already establish a safe read-only, idempotent operation, yet the description adds substantial behavioral texture on top: the fixed verification cadence (day 28, then 45/60/75, final at 90), the caveat that 'a horizon appears only once it has been measured,' the fact that before_window appears only on the first page, and the 90-day-per-call ceiling. These are non-obvious traits an agent could not infer from annotations or schema.

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?

The opening clause is well front-loaded, but the remainder is a single run-on sentence of roughly 100 words that chains the stage list, the verification cadence, the metric inventory and the before_window rule together. All the content is relevant, yet the lack of sentence breaks or ordering makes it harder to parse than its density warrants.

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 burden of describing the return payload, and it does so: stage progression, per-horizon sample sizes, citation/mention/AI-referral movement, and the before_window object. What it omits is the concrete shape of an individual step record, leaving the agent to infer fields from the prose.

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 per-parameter baseline would be 3. The description earns more by clarifying runtime semantics the schema does not: the 90-day maximum window expressed as the 'last N days is since = today minus N-1' arithmetic, and that paging continues via next_cursor rather than offset. It does not, however, explain how the stages filter interacts with before_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?

The description names a specific resource — the brand's full loop timeline from buyer question tracked through gap found, draft created, published, fix shipped, page changed and verified — and states sort order (oldest first). An agent gets a clear picture of what is returned. It stops short of naming the sibling it differs from, notably get_fix_verification and get_changes, which cover adjacent territory.

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 through the 90-day window rule and the since/until arithmetic ('since = today minus N-1, today counted'), which tells the agent how to scope a call. However, there is no explicit statement of when to reach for this tool versus get_fix_verification or get_changes, and the only routing hint is the incidental 'brand_id from list_brands.'

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