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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=false and destructiveHint=false, so the agent knows this is a non-destructive but mutating, non-idempotent write. The description usefully adds the business rule that only ratings tied to a real order are accepted, but says nothing about duplicates (error vs. append), immutability, or auth requirements — gaps that matter for a non-idempotent mutation.

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 tight sentences, no filler. The operational purpose is front-loaded and the second sentence earns its place by stating the hard constraint and why it exists for the platform's reputation.

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 4-parameter mutation with no output schema and no parameter descriptions, the description covers the essential precondition but leaves meaningful gaps: duplicate-rating behavior, whether the comment is optional, error handling for an invalid code, and permission requirements. There is no output schema to explain return values, so that omission is acceptable.

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 only 25% — just 'slug' for provider — so the description must compensate and partially does, revealing the code format (LQ-XXXX) and that the provider is the professional who received the order. It adds nothing about the optional comment field or the rating scale beyond what the integer 1–5 bounds already encode in the schema.

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 verb and resource: it registers a user's rating for the professional who served their request, and scopes it to an existing order code (LQ-XXXX). That is unambiguous and clearly distinct from retrieval/listing siblings like get_provider or get_request, though no sibling is named explicitly.

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 states one real precondition — the rating must be linked to an actual order ('Só aceita avaliação ligada a um pedido real') — which tells the agent when a call will be rejected. However it never states when to use this tool versus alternatives (e.g., after get_request completes), so usage is only implied.

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