api_call

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

With no annotations provided, the description must carry the behavioral burden, and it does disclose the most important risk: WRITE methods execute for real in live mode. It also directs agents to external documentation for method-specific behavior. It omits return format and error behavior, but the live-write disclosure is substantial and directly relevant to safe invocation.

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 two sentences with no filler: purpose, safety warning, and routing are all present. The most important operational fact, that writes execute in live mode, is front-loaded and cannot be missed.

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 passthrough tool, the description gives the essential context: what it calls, how it calls it, the live-write behavior, and how it relates to the named sibling tools. The external API documentation link fills in the long tail of method-specific details. It does not describe response shapes or error handling, but the external reference and low parameter count keep this 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?

The schema has 0% description coverage, so the description must compensate. It does add meaning by explaining that 'method' is a DomRobot method name and 'params' are raw parameters, and it links to the full API documentation. However, it provides no concrete examples or per-method parameter guidance, so the compensation is only partial.

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 verb ('call'), resource ('any DomRobot method'), and mode ('by name with raw params'). It also differentiates itself from the named sibling tools by positioning itself as the generic fallback. This leaves no ambiguity about what the tool does.

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 instruction to 'prefer the named tools' gives agents a clear default-versus-fallback decision rule. The warning that WRITE methods execute for real in live mode adds a critical when-to-be-careful condition. It does not explicitly state 'use only when no named tool exists', but the precedence is strongly implied.

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