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

With no annotations, the description carries the full burden and does well: it discloses that corrections are authoritative, override the system guess immediately, and survive monthly auto-regeneration — persistence semantics that are not derivable from the schema. It also flags that giftLed has downstream effects on gift-holiday relevance and instructs confirmation to the user. It stops short of covering permissions/authorization or partial-failure behavior.

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?

Front-loaded with the trigger condition and the hard constraint, then supporting detail. Every clause carries weight, including the parenthetical examples, which disambiguate the kind of correction intended. Slightly dense with example quotes but not wasteful.

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 9-parameter mutation tool with no annotations and no output schema, the description supplies the trigger, the authority/persistence model, the standout field, and the post-save confirmation behavior. The remaining parameters are fully covered by the schema, so nothing an agent needs to call it correctly is missing; only return-value detail is absent, and that is minor here.

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 the schema already documents all nine parameters and a baseline of 3 applies. The description adds real meaning beyond the schema for giftLed, explaining why it matters (retail gift-holiday relevance) and emphasizing it as the high-stakes field, which is exactly the extra semantic layer the schema does not provide.

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 ('Correct a store's profile') and immediately bounds the scope to user-stated corrections, which cleanly separates it from read siblings like get_store_profile and set_intervention. The quoted user utterances make the intended trigger concrete rather than abstract.

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?

Explicitly states when to call ('when the USER tells you it's wrong') and when not to ('ONLY call this from something the user stated about their own store — never from your own inference'). The negative constraint is the exact failure mode an agent would otherwise fall into, and it is stated unambiguously.

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