perseus_tool

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

Beyond the annotations (destructiveHint: true), the description explicitly states 'Destructive — executes the tool with the user's permissions.', adding important behavioral context. It also clarifies that execution is for allowlisted tools only, which is not covered by annotations.

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 three short sentences, each adding essential information: action, usage condition, and behavior. It is front-loaded with the main purpose and contains no redundant or irrelevant detail.

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 simple tool with one parameter, full schema coverage, annotations for destructiveness, and the presence of an output schema (not shown but indicated), the description provides sufficient context. It covers purpose, usage, and behavior, leaving no critical gaps for an AI agent to misinterpret.

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 input schema already has 100% coverage for the single parameter 'name' with a description. The tool description adds no additional semantics about the parameter beyond what the schema provides, so the baseline score of 3 applies.

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 'Run' and resource 'external tool that has been allowlisted', distinguishing it from many sibling tools that are specific internal tools. It explicitly mentions the allowlisting requirement, making the purpose unambiguous.

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 provides guidance on when to use: for approved integrations only, and requires the tool name to be in the allowlist. It does not explicitly list when not to use or name alternatives, but the context of sibling tools implies this is for external tools not covered by other perseus_* tools.

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