firestarter_request_escrow

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

Annotations are minimal (readOnlyHint=false, openWorldHint=true, destructiveHint=false), so the description carries the behavioral burden. It goes beyond annotations by revealing that the tool creates an escrow invite (a side effect) without directly contacting the seller—the buyer must manually send the message. It also discloses that the fetch may be blocked on certain platforms, and that providing title/price yields a usable invite even on fetch failure. This is critical behavioral context for an agent.

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 effective: it packs a lot of critical context (buyer-side, manual messaging, fetch block, parameters) into a few sentences. It is front-loaded with the primary purpose and proceeds to key usage details. Slightly long, but every sentence contributes essential information, so it earns a 4 rather than a 5.

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?

The tool is complex (external integration, seller invite, notification), but the description covers the workflow, failure modes, and parameter usage. It explains the seller claim link, where notifications go, and the fallback for blocked fetches. With no output schema, it doesn't describe return values, but the return is likely minimal (invite link), and the description provides enough for an agent to act. No major gaps.

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%, so parameters are well-defined in the schema. The description adds value beyond the schema by clarifying the role of buyer_email (where the goes-live notification lands), explaining that title and price are buyer-supplied to compensate for blocked fetches, and indicating that source_url is the external listing URL. It also states that buyer_name is shown to the seller on the claim page, which the schema does not mention.

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 tool's buyer-side purpose: to pay for an external listing via Firestarter escrow. It specifies the action (create an escrow invite) and the resource (the listing), and distinguishes it from other firestarter_ tools by its invocation context (found a listing on another site). The mention of 'Firestarter never contacts external sellers' and the seller claim link makes 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 explicitly says when to use this tool (buyer found a listing on an external marketplace and wants escrow) and implies when not to (when not buying from an external site). It also provides crucial guidance on the requirement to send the message manually, handling of blocked fetches for specific platforms, and the need for buyer email and listing URL. This guides the agent on required fields and fallback behavior.

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