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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety and idempotency profile is fully covered by structured data. The description's only added context is which policy categories are returned; it says nothing about per-company availability, error behavior when a policy type is absent, or what the response contains.

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 short clause with the verb front-loaded and zero padding; nothing is redundant. It is arguably under-elaborated for an agent that needs to know the default and scope, but as structure and economy go it is close to ideal.

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 simple, read-only, two-parameter retrieval tool with complete schema descriptions, safe annotations and no output schema, the description is nearly sufficient. The remaining gap is that it doesn't signal that results are scoped to one company or what happens when a requested policy type doesn't exist.

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% and both parameters are documented enums, so the schema carries the full burden. The description restates the four policy types but omits the 'todas' default value and the company slug option, adding essentially nothing beyond the schema — 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 gives a specific verb ('Retorna') and resource ('políticas') and enumerates the policy domains (troca, entrega, pagamento, garantia), so an agent immediately knows what it retrieves. It does not explicitly distinguish itself from siblings like get_faq, but the sibling set covers unrelated resources, so differentiation is largely implied.

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 only implied: the enumerated policy types suggest the tool is for customer-facing policy questions, but there is no explicit 'use this when...' statement or mention of an alternative (e.g., get_faq for general questions). Nothing is misleading, but nothing guides selection either.

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