inspect

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

The description provides rich behavioral context that goes far beyond the annotations. It explains the financial constraints (1% fee, 0.001 USDC floor), the authorization requirements (owner opt-in, shared process limits), which are essential for an agent to execute this stateful operation safely.

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 very dense and heavily weighted toward policy and financial disclosure. While all content is necessary, the sentence structure is complex and requires the agent to parse multiple nested constraints (fee, floor, opt-in, shared authorization) in a single block of text.

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?

Despite lacking an output schema, the description successfully covers the 'cost' and 'governance' aspects of the tool. By detailing the fee structure and authorization prerequisites, it provides almost all necessary context for a complex operation.

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 description adds crucial domain knowledge to the 'url' parameter, specifying that 'API rejects private URLs before payment.' This nuance is vital and not captured in the schema, significantly improving parameter understanding.

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 defines the purpose: reading stored evidence for a specific endpoint URL without initiating a new call or payment. It distinguishes itself from siblings like 'recommend' or 'receipt' by focusing specifically on the act of 'inspect[ting]' and quoting.

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?

While it doesn't provide a direct 'if-then' usage guide, it strongly implies usage by detailing the payment mechanism, fee structure (1% floor), and the need for owner opt-in. This gives the AI sufficient context on when the operation is applicable.

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