rpc_call

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

No annotations are provided, and the description only labels it as a 'whitelisted agent RPC' without disclosing side effects, permissions required, or what the RPC does. For a debug tool, details about its behavior (e.g., potential system modifications) are missing.

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 a single sentence, concise and front-loaded with the critical guidance to prefer other tools. It efficiently conveys the essential point without fluff, though a bit more structure could clarify usage.

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 low specificity (no output schema, no annotations, generic parameters), the description fails to provide sufficient context. It does not explain what the RPC returns, how to use 'args', or what RPC names are valid beyond the example 'windowFrame'.

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 only 50% (name has description, args does not). The description does not add any meaning beyond the schema; it does not explain what 'args' is for or how to format it. The empty items schema for 'args' is unhelpful.

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 states it is a 'whitelisted agent RPC' and advises to prefer first-class tools and probe_help, which clearly indicates it is a debug/fallback tool. This distinguishes it from sibling tools by positioning it as a last resort.

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 explicitly advises to prefer other tools ('first-class tools + probe_help'), giving a clear when-to-use guidance. However, it does not specify when exactly to use this tool or what conditions warrant its invocation, leaving some ambiguity.

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