firestarter_create_market

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses important behavioral traits: creating a market does not require seller status/Stripe/payout-supported country, `share_bps` is capped and the response returns the effective value, and a taken `handle` fails the entire create operation. It also clarifies that a payout method is only needed later, and outlines the follow-up call to get a share code.

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 front-loaded with a clear purpose, then usage guidance, then key constraints, and finally the handle workflow and next step. Every sentence earns its place; the length is justified by the tool's complexity and the need to prevent common misroutes. There is no internal redundancy.

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 description covers prerequisites, exclusions, failure conditions, parameter caps, and follow-up actions, which is strong for a tool without an output schema. However, it does not fully describe the successful response beyond the effective `share_bps` value, so an agent may not know exactly what the tool returns (e.g., program ID or handle). This is a minor gap given the tool's complexity.

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 the description does not need to compensate. However, the description adds little beyond the schema: `share_bps` and `handle` details in the text largely replicate the schema's own descriptions, including the later set handle behavior. It does not add new per-parameter meaning for `type`, `tagline`, or `display_name`.

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 ('Set up') and resource ('community/affiliate market on Firestarter'), and clearly states it creates an attribution program owned by the caller. It also distinguishes the tool from siblings by explicitly directing users to call this tool rather than seller onboarding and by referencing follow-up tools like firestarter_market_link and firestarter_set_market_handle.

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?

It provides explicit when-to-use guidance: 'Use this WHENEVER a user asks to create, set up, or start a community market, affiliate program, or store for my audience.' It also includes exclusions ('do NOT route them through seller onboarding or ask about their country') and explains that a payout method is only needed later, not now. Alternatives and next steps are named.

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