firestarter_verify

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

The annotations only indicate readOnlyHint: false and destructiveHint: false. The description adds rich behavioral context: the FS-XXXX code written by hand, the two-state outcome (match vs. mismatch), the fact that unreadable photos are held for review rather than rejected, and the follow-up activation step. This gives the agent a clear mental model of the tool's side effects and state transitions beyond what structured fields declare.

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 dense but not padded - it front-loads the core action, then the trigger conditions, then walks efficiently through the workflow and outcomes. The parenthetical trigger list is concise, and the three-state outcome paragraph is economical. The only slight inefficiency is that 'photographs the paper next to the item, and sends the photo in chat' contains slightly more narrative color than strictly necessary, but it does clarify the expected photo composition.

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 tool acting as a checkpoint in a multi-step flow, the description covers everything an agent needs to call it correctly: the trigger conditions, the exact required format (handwritten code, photo content), the follow-up action (activate via firestarter_update_listing), and the full range of outcomes including the edge case of an unreadable photo. With no output schema required, the description does not overhang its bounds.

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 100% - both listing_id and photo_url have useful descriptions. The description adds some narrative context that connects the parameters ('sends the photo in chat - pass that photo's URL here with the listing ID') and provides the FS-XXXX format detail for the code. The description reinforces the parameter relationship but doesn't need to be heavily relied upon for parameter understanding; the schema already carries that weight effectively.

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 specific verb-resource pairing ('Submit a possession-verification photo for a listing whose activation asked for one') and immediately scopes the tool with concrete trigger conditions (high-value >= $500, luxury category, source-URL conflict). The purpose is unambiguous and easily distinguished from siblings like firestarter_update_listing or firestarter_upload_image, which handle different steps in the workflow.

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 states when this tool applies (activation asked for a photo) and names a sibling (firestarter_update_listing) for the follow-up step ('then activate via firestarter_update_listing'). It also clarifies what content the photo must contain (handwritten FS-XXXX code next to the item) and the three possible outcomes (instant match, flagged mismatch for resubmission, held for review), leaving almost no ambiguity about when to invoke this tool versus alternatives.

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