erpnext_call_method

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

Annotations already convey destructive=true and readOnly=false, so the description does not need to restate those. It adds useful context by noting that unlisted methods require review and that the correct response is not to edit an allowlist, which is valuable governance/behavioral guidance for a powerful generic RPC tool.

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?

Two short sentences, with the core action front-loaded and a concise safety policy second. There is no filler or redundant restating of 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?

For a broad, potentially destructive RPC tool with five parameters and zero schema description coverage, the description is too thin. It does not explain method naming conventions, how dry_run behaves, when to switch http_method or api_version, or how this relates to the established sibling tools. The output schema reduces some burden, but the invocation context remains under-specified.

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 carries the burden of explaining parameters, but it only mentions the concept of a method. The roles of args, dry_run, http_method, and api_version are left entirely to inference from names, enums, and defaults; the description adds no parameter-level meaning.

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 verb and resource: call any Frappe-exposed RPC method. The word 'any' signals that this is the generic escape-hatch tool, which helps distinguish it from the many higher-level ERPNEXT sibling tools for specific operations. It lacks an explicit sibling comparison, so it stops just short of a perfect score.

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 phrase 'Unlisted methods need review, not an allowlist edit' implies a governance boundary: this tool can call methods beyond the normal allowlist, but they require review. It does not explicitly state when to prefer specific siblings such as erpnext_api_request or the doc_* tools, so usage guidance is only implied rather than explicit.

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