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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered by structure rather than description. The description adds value by noting bulk execution via customer_ids and identifying the supported filters (search, page). It aligns with the annotations (read-only, non-destructive) and adds the batching behavior, but does not describe the return format or pagination semantics, so it is adequate but not rich.

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?

The description is compact and front-loads the core purpose effectively. Some structure is wasted documenting the 'get' action that is not this tool (flattened to list), which is redundant given the separate get sibling. The '[Flattened action: list]' note helps disambiguate but adds a maintenance burden that could be avoided by simply documenting list-only behavior.

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 5-parameter tool with 0% schema coverage and no output schema, the description should clarify every parameter and the return behavior. It covers search, page, customer_id, and customer_ids in intent but leaves 'account' undocumented and does not describe what the list response contains. The get/list conflation further undermines completeness. Adequate for a read-only tool whose safety is carried by annotations, but gaps remain.

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?

With 0% schema description coverage, the description must fully compensate, and it partially does: it explains search and page as list filters, customer_id as the get selector, and customer_ids as the bulk parameter. However, the 'account' parameter is left entirely unexplained, and the dual list/get framing conflates which parameters apply to this flattened tool. The description covers most parameters but not all.

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 opening line 'Leitura de clientes na Cakto (para análise/CRM)' states a clear verb (read) and resource (Cakto customers) with a stated use-case (analysis/CRM), which distinguishes purpose well. However, the description documents both 'list' and 'get' actions while declaring '[Flattened action: list]', so the dual-action framing somewhat muddies what this specific tool actually does.

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?

The description implies a list-vs-get distinction ('get requer customer_id') and notes bulk support via customer_ids, but never explicitly routes to the natural sibling cakto_customers_get. Given that a dedicated single-customer sibling exists, the in-description 'get' instructions are borderline misleading — an agent might try to fetch a single profile through this tool instead of the sibling. No explicit when-to-use vs alternatives guidance is provided.

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