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

Annotations already convey readOnlyHint=false and destructiveHint=true, and the description adds substantial behavioral nuance: spending exactly one credit, the requirement for a new city_credit_request_id, the exactness of drawing shapes, and 'Variants never select randomly.' It does not explicitly detail what the destructive operation affects (e.g., publishing a public kind) but goes well beyond annotation basics.

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 well-organized: purpose first, then parameter details, then operational workflow, then fallback pointers. Every sentence adds necessary constraints or guidance. It is longer than some, but the complexity of the tool justifies the verbosity; no fluff is present.

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 9-parameter tool with no output schema, the description covers the essential operational flow: payment preflight, drawing shape rules, variant constraints, and parameter limits. It omits a description of the return value or response format, which would be helpful but is not critical for correct invocation. The references to draw_self and the catalog provide additional context.

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?

With schema description coverage at only 44%, the description compensates richly. It explains name uniqueness and normalization, trait uniqueness and existence, recipe uniqueness and size limits, drawing shape options, variant uniqueness and state, and the payment identifier purpose. It adds meaning far beyond the raw schema, especially for recipe and drawing_variants constraints.

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 opens with 'Invent a public kind for the exact $1 city fee,' a precise verb-resource-fee statement. It distinguishes itself from siblings like revise_kind by the act of inventing, and later references draw_self and credit_preflight, which clarifies its scope. The purpose is unambiguous and immediately actionable.

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 instructs when to call credit_preflight before confirming, how to choose between city_credit_request_id and X-PAYMENT header (including 'never send both payment rails'), and names front_door as an alternative for navigation. It provides clear context on when to use this tool and what steps must precede or accompany the call.

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