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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it discloses that results are paginated ('in pages'), that omitting `logradouro` and `numero` causes paging through the entire CEP, and it describes the returned fields ('complement' and 'type').

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?

Three sentences, front-loaded with what the tool returns and followed by the key distinction from the CEP lookup and the filtering behavior. Every sentence contributes to understanding; no redundant or vague phrasing.

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, the description adequately compensates by naming the returned fields (complement, type) and the paginated nature of results. It also covers the interaction of the optional filters. It does not explain error handling or the exact pagination metadata, but for a read-only, idempotent tool with fully described parameters, this is nearly complete.

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%, so the baseline is 3. The description adds meaning beyond the schema by explaining the interaction between the optional `logradouro` and `numero` filters and the default behavior: without them, the tool pages through all units of the CEP. This clarifies the filtering role of those parameters in a way the individual schema descriptions do not.

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 states a specific resource ('units at a CEP (apartment, store)') and what is returned ('with the complement and the type, in pages'). It clearly distinguishes this tool from the CEP lookup sibling by explaining that the lookup groups by street and number while this tool returns each unit.

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 provides a clear context for use: when you need individual units rather than the grouped CEP level. It also states the condition 'Without `logradouro` and `numero`, it pages through the whole CEP,' which helps the agent decide when to supply those filters. However, it does not explicitly name an alternative tool to use when this tool is not appropriate, so a 4 rather than a 5.

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