evaluate_tool_call

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates that the tool is advisory rather than executing ('Ask ... whether'), but it does not disclose the return shape, side effects, latency, permissions, or whether an unsafe result triggers an approval workflow. This is minimal transparency beyond the schema.

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, front-loaded sentence with no filler; every word contributes to stating the tool's purpose. However, the brevity leaves out behavioral and usage details, making it concise but slightly under-specified.

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 security-evaluation tool with no annotations, no output schema, and a free-form arguments object, the description is too thin. It does not state what the response contains, when to use this tool relative to guarded_action or resolve_approval, or how the arguments are validated. An agent can make a first guess but lacks enough detail to call confidently.

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%, and the description does not explain tool_name or the arguments object. 'Proposed tool call' loosely implies both parameters, but it never clarifies that tool_name must reference a registered tool or that arguments should mirror the call being evaluated. The free-form arguments object remains largely undefined.

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 uses a clear verb ('Ask'), names the resource ('MCP Guardian'), and defines the object ('proposed tool call'), making the core function obvious. It doesn't explicitly distinguish itself from siblings like guarded_action or resolve_approval, but the 'safe to execute' framing makes its advisory nature reasonably clear.

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?

No guidance is given on when to call this tool versus alternatives. The description implies a pre-execution safety check, but it does not state that guarded_action should be used to actually run the call, nor what to do if the result is unsafe. Agents must infer usage context from the name and sibling list.

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