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

Annotations only supply generic hints (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description carries the real burden: a fee is charged, validation refuses before any fee, omitted fields are preserved, traits and drawing_variants are whole-list replacements with a warning to resend everything, and dropped_traits is surfaced in the answer. The credit flow (preflight, fresh suggested_request_id, retry identifier) explains the non-idempotent payment behavior the annotations only imply.

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?

Front-loaded with the essentials (revise, fee, kind_id required, omission semantics) in a compact block. A few sentences are run-on or redundant, such as repeating the 4,000-character description limit already enforced by the schema, and 'never rewrites an older revision or randomly selects for things' is awkwardly worded, but almost every clause carries a real rule.

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 paid mutation with no output schema and no annotations beyond hints, the description is unusually complete on preconditions, refusal ordering, and replacement semantics. It falls slightly short by only hinting at the response ('the answer's dropped_traits') and omitting the recipe constraints, but nothing critical to calling it correctly is missing.

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 44% schema coverage, the description compensates well: it explains that omitted optional fields keep current values, that traits replaces the entire list and accepts at most 32 unique existing trait names, and that drawing/drawing_state/drawing_description must be paired per draw_self. Gaps remain on recipe (its row/ingredient/byte limits live only in the schema) and no explicit guidance on drawing_variants' interaction with drawing.

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 opening clause gives a specific verb, resource, ownership constraint, and price: 'Revise a kind you own for the exact $1 city fee.' It is clearly distinct from invent_kind and from the law-related steps it explicitly refuses, so an agent can route correctly without opening the schema.

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 states prerequisites (you must own the kind, no open sale offer), the exact paid-action sequence (call credit_preflight first, then either a new city_credit_request_id or omit it for outer X-PAYMENT, never both), and the escape hatch ('Lost? Call front_door'). It also names the alternative path for law traits rather than leaving the agent to guess.

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