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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds the result-ordering notion ('mais recentes') and the rationale that contact lookup avoids manual name/phone matching, but says nothing about result volume, empty-result behavior, or what happens when both filters miss.

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 sentences, front-loaded with the resource and return fields, then the conditional branch for contact-specific lookup. The parenthetical example earns its place by showing the intended call chain; only minor trimming would be possible.

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?

There is no output schema, and the description compensates by naming the fields returned (canal, status, última mensagem) and the default recency ordering. Combined with fully documented parameters and read-only annotations, an agent has enough to call it correctly; only the status-filter interaction with contact filters is left to the schema.

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 every parameter including the contact_id vs contact_phone tradeoff and the limit cap is already documented in the schema. The description reinforces that contact_id is the precise route and can be obtained from get_contact/list_contacts, but contributes no additional syntax or constraint detail. 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?

States a specific verb and resource ('Lista as conversas mais recentes com clientes') and enumerates the fields surfaced (canal, status, última mensagem). It also distinguishes the two operating modes — global overview vs. single-contact lookup. It stops short of naming adjacent siblings like list_inbox or get_conversation_messages, so the boundary is not fully explicit.

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?

Gives concrete usage contexts: overview of atendimento, or pass contact_id/contact_phone to find one contact's conversations. It even sequences the call after get_contact/list_contacts, which is genuinely actionable. No explicit 'when not to use' or alternative-tool routing (e.g., when to prefer list_inbox instead).

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