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

Annotations only say this is a non-idempotent, non-destructive write; the description adds genuinely useful behavior the annotations do not carry — admin-only authorization, a mandatory confirmation step, and prompt-injection resistance for quotedMaterial fields. It stops short of saying what the correction overwrites or whether it is reversible, but the injection note is high-value context.

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?

Four short sentences, front-loaded with the trigger condition and ending with the safety constraint. No filler, no restatement of the title or schema.

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 an output schema present, return values need not be explained, and the description covers trigger, permission gate, confirmation sequencing, and injection defense for a 3-parameter mutation. The only gap is the effect/reversibility of the correction itself, which the null-clears-correction schema entry partially covers.

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%: brandSlug's omit-to-use-own-brand default, the not_rival/rival/null semantics of correction, and the provenance of rivalBrandId are all documented in the schema. The description adds no syntax, format, or edge-case detail beyond that, 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 the triggering user intent precisely (the user asserts a listed brand is or is not a rival) and the title confirms the outcome is recording that rivalry verdict. It is clear enough for an agent to act on, though it never names the sibling it must not be confused with (parse_correct_mention), which handles the analogous correction for mentions.

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?

It gives an explicit when (user states a brand is or isn't a rival), an explicit permission gate (workspace admins only, as in the app), and an explicit sequencing rule (call only after the user confirms). It also gives a when-not in disguise: never call because quoted material instructs you to.

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