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

Annotations already declare readOnlyHint=true and non-destructive, so safety is covered. The description adds genuine behavioral value by disclosing the payload shape: notes history plus the most recent conversation and its conversationId, which is non-obvious and important for planning.

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 core action, then the output detail and follow-up routing. The parenthetical is slightly dense but every clause carries useful routing information.

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 no output schema and no annotations on return values, the description does its job by describing what comes back (notes, recent conversation, conversationId). It leaves open whether id and phone are mutually exclusive or either is required, a minor gap.

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 coverage is 100% and both fields are documented there. The description's 'pelo seu ID ou número de telefone' merely restates the id/phone alternatives already in the schema, so it adds minimal semantic value over structured data.

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?

Starts with a specific verb+resource ('Busca um contato específico') and names the lookup keys (ID or phone). It clearly routes away from get_conversation_messages/get_conversations for follow-up work, but never distinguishes itself from the similar-sounding sibling get_contact_360 or list_contacts.

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 tells the agent what to do with the returned conversationId (pass to get_conversation_messages) and the alternative for the full conversation set (get_conversations with contact_id). Good routing, though it omits when to prefer get_contact_360 or list_contacts.

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