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

Annotations already define the tool as readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description need not repeat this. It adds value by explicitly stating the 'get' action and bulk support, which are behavioral traits beyond the annotations. It also notes that it's a 'diferencial' of Kommo, but this is marketing. The description does not mention any side effects, but they are consistent with a read-only get operation.

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 relatively concise, but it includes a note about the 'list' action and a bullet point for bulk support that is somewhat redundant with the mention of ids. The structure is a bit ad hoc: it mixes description, a bracketed note about the flattened action, and then bulk support. It could be tighter, though it is not overly verbose.

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 6 parameters, no output schema, and 0% schema description coverage, the description should do more to explain the parameters and return behavior. It explains the purpose and gives a hint of filters, but it doesn't describe the expected response or how to use 'id' vs 'ids' effectively. For a get operation, it might be sufficient, but the bulk support and filter parameter are left undefined, leaving gaps for the agent.

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 0%, so the description must compensate for the parameters. It mentions 'filter' only for the list action, but since this is flattened to 'get', it doesn't explain 'id' or 'ids' explicitly, though those are obvious from the action. The description doesn't describe what 'account' does or how 'page' and 'limit' relate to get operations. It adds minimal meaning beyond what the schema provides; the context of 'get' implies id usage but lacks detail.

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 clearly states this tool handles 'Conversas (talks) do inbox unificado' and specifies the 'get' action for retrieving a talk by id, which is distinct from listing. It also differentiates it by highlighting it as 'o diferencial do Kommo' for WhatsApp/Instagram/Telegram history, distinguishing it from sibling list tools.

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 explains the tool supports 'get' for a single record by id and also mentions 'Bulk support: accepts ids for batched execution', which indicates usage for single or batch retrieval. It doesn't explicitly state when not to use it, but the context of 'inbox unificado' and the presence of sibling tools like kommo_talks_list implies when to use this get variant. No explicit alternative is named, but the action selection is clear.

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