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

Annotations already declare non-destructive, idempotent write behavior, but the description adds genuinely new context: rejection blocks re-detection and is reversible through update_brand. That reversal path is the key nuance an annotation cannot express. Return/rate-limit behavior is not covered, keeping it short of 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?

A single dense sentence with the state change front-loaded, followed by the recovery path and the error-reporting clause. No filler; every clause carries new information.

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 compensates by documenting the `skipped` return field and the hidden-state side effect. Together with the fully-covered schema and annotations, an agent has everything needed to call it correctly.

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 error semantics for `ids` — IDs that are missing or not suggestions land in `skipped`. That tells the agent partial failure is possible and how it surfaces, which the schema does not say.

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?

States a specific verb+resource ("Reject suggested brands") and immediately distinguishes it from the sibling approve_suggested_brands by naming the resulting state. An agent can tell at a glance this is the negative counterpart to approval, not a delete operation.

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?

Explains the effect of using it (moves to "hidden"/"Not tracking"), implies the resumption path via update_brand, and warns that non-suggestion or missing IDs are skipped. It lacks an explicit statement of when NOT to reject (e.g., vs delete_brand), so it stops short of full routing guidance.

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