CiviCRM APIv4 passthrough

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

With no annotations provided, the description carries the full burden. It discloses that the tool is disabled unless certain environment variables are set, and that writes and deletes have additional requirements. This alerts the agent to write and delete capabilities without explicitly stating 'this tool can modify data,' but the mention of 'deletes need CIVICRM_ALLOW_DELETES' implies destructive potential. It could add a caution about irreversible actions, but it is sufficient.

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 three sentences long, front-loading the purpose first, then constraints, then guidance. Every sentence provides essential information with no 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's complexity (generic API passthrough with no output schema), the description covers key aspects: what it does, its constraints, and a suggestion for pre-checking fields. It does not explain the return format or error handling, but since it is a passthrough, the response format is standard CiviCRM API response, which may be assumed. It is reasonably 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 says 'Accepts entity + action + params,' which is a restatement of the required parameters. It does not add additional semantics beyond what the schema provides, such as explaining the structure or constraints of the params object. Thus, no extra value.

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 explicitly states 'Generic APIv4 call. Accepts entity + action + params.' This clearly defines the tool's purpose as a generic passthrough to the CiviCRM APIv4, distinguishing it from the many sibling tools (e.g., civicrm_get_contact) that handle specific entities and actions.

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 explicit when-to-use guidance: it is a generic API call. It also gives when-not-to-use: 'Disabled unless CIVICRM_ALLOW_GENERIC_API=true; writes additionally need CIVICRM_ALLOW_WRITES and deletes need CIVICRM_ALLOW_DELETES.' It additionally suggests an alternative: 'Use civicrm_describe_entity first if unsure of field names.'

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