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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds real value on top: the verdict vocabulary (moved / within_noise / awaiting_samples), the exclusion of non-fix rows, and the auto_detected provenance marker. It does not say how long 'awaiting_samples' persists or whether results are recomputed on each call, which keeps it from a 5.

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 sentences, no filler, and the inclusion/exclusion and verdict semantics are packed efficiently. The opening clause is dense and the verdict list arrives late, so front-loading could be slightly better.

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 and does so at a high level: per-fix before/after mention rate plus verdict labels. It remains silent on result freshness, pagination beyond the schema's limit, and empty-result behavior, so it is strong but not exhaustive.

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 limit, brand_id, and fix_event_id are already fully documented in the schema. The description only reinforces brand scoping and the single-fix case without adding format or edge-case detail beyond the schema, which is the baseline 3 situation.

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 verifiable resource and what it returns: every fix marked shipped for a brand, with mention rate before/after and a verdict. It is easily separable from siblings like get_visibility and list_fix_opportunities because it is scoped to shipped fixes and their measured outcome.

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: an agent can infer this is the post-shipment follow-up to mark_fix_shipped, but neither that sibling nor any alternative is named, and no when-not condition is given. The exclusion mentioned ('Not a fix' rows) concerns result content, not tool selection.

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