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

Annotations already indicate non-read-only, non-idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: it clarifies that unlink modifies relationship references rather than deleting records, explains behavior per relationship cardinality, and discloses bulk support. It does not mention failure modes or return behavior, but the provided safety profile is reasonably complete.

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 appropriately short and front-loaded with the core function, followed by relationship-specific semantics and then bulk support. Every sentence contributes new information without redundancy or filler.

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?

Given the tool has 7 parameters, 0% schema description coverage, no output schema, and no parameter descriptions, the description is incomplete. It covers the core unlinking concept and bulk support, but does not explain required fields like object, id, and field, nor what the operation returns or how errors are handled.

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 0%, so the description must compensate for parameter meaning, but it only partially does so. It clarifies target_id, ids, and target_ids in the context of bulk/unlink behavior, but leaves critical parameters like object, id, field, and account unexplained. In particular, the relationship between id and ids, and the exact role of field, remain ambiguous.

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 the tool's purpose: 'Desfaz uma relação' (breaks a relationship), with concrete semantics for many ('remove o target_id do conjunto') and single ('limpa o campo') relationships. This distinguishes it from sibling tools like crm_link_record and crm_delete_records, as it is explicitly about unlinking rather than deleting records.

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 provides useful context on when to use the tool by explaining how it behaves for 'many' vs 'single' relationships and by noting bulk execution support. It does not explicitly name alternatives or state when not to use it, but the context is clear enough to guide selection among sibling tools.

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