api_call

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

With no annotations present, the description carries the full disclosure burden and uses it well by warning that the tool 'can invoke destructive operations' and is gated by ISPCONFIG_READONLY. This flags the two most decision-relevant behaviors for an open-ended passthrough. It stops short of disclosing auth requirements or failure/error behavior for invalid methods, but the core risk is squarely stated.

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 sentences with zero padding: the first declares function and scope, the second delivers the safety warning. The verb and resource are front-loaded, and the most safety-critical information is placed in an attention-capturing NOTE.

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 generic dispatcher whose method space is unknowable, the description covers the two essential facts: it exists for uncovered methods and it can be destructive/disabled. No output schema exists, and the description cannot enumerate returns for arbitrary methods, so nothing critical for selection is missing. Additional response or error-shape context would help but is not essential for a passthrough.

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%, with 'method' described by name and example ('mail_fetchmail_add') and 'params' described as 'Method parameters.' The description adds no param-level detail, which is acceptable because the schema fully documents both parameters and the second is intentionally a catch-all object.

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?

States a specific verb ('Call'), resource ('any ISPConfig API method'), and frames itself as an 'escape hatch for methods not covered by other tools,' which clearly distinguishes it from the 60+ sibling tools that each wrap one specific method. An agent can immediately identify this as the universal fallback rather than a duplicate of a specific-operation tool.

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 'escape hatch for methods not covered by other tools' is an explicit when-to-use rule: prefer dedicated siblings and fall back only when no sibling covers the method. The note that it is 'disabled when ISPCONFIG_READONLY=true' additionally signals when the tool is unavailable and hints that it may be blocked in read-only contexts.

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