Liga um registro a outro por um campo de relação (ex.: vincular um contato a uma empresa). Para relação 'many' adiciona ao conjunto; para 'single' define o alvo.
Bulk support: accepts ids, target_ids for batched execution.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| ids | No | ||
| field | Yes | ||
| object | Yes | ||
| account | No | ||
| target_id | Yes | ||
| target_ids | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral transparency beyond the annotations: it explains that many-relationships add to a set, single-relationships set a target, and that batches are supported. It does not contradict the annotations; readOnlyHint=false is consistent with a linking mutation.
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 concise and well-structured: it front-loads the core purpose, provides a concrete example, then adds cardinality and bulk support details. Every sentence adds value without restating the schema or annotations.
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?
This is a mutation tool with 7 parameters, 0% schema descriptions, and no output schema. The description covers the primary use case and bulk behavior, but it leaves some context empty: what account/object mean, how errors behave, and what the caller should expect after execution.
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?
The input schema has 0% parameter description coverage, so the description has to compensate. It does clarify ids/target_ids for bulk execution and mentions the relationship field semantics, but it leaves important parameters like account, object, and singular/plural relationships under-explained.
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 core action: linking a record to another via a relationship field, with a concrete CRM example (contact to company). It also differentiates behavior for 'many' versus 'single' relationships and distinguishes itself from siblings like crm_unlink_record.
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 clearly conveys when to use the tool: when linking records, including cardinality-specific behavior and bulk support via ids/target_ids. It does not explicitly name alternatives or exclusion cases, such as 'use crm_unlink_record to remove links,' but the context is otherwise clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.