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

Goes well beyond the annotations: it discloses the 1-credit cost, the free-allowance case, the quote-first/two-step paid flow, that nothing starts before confirmation, which sibling redeems the quote, what the iter0 card displays and that it self-updates, and how the results are subsequently built. These are exactly the consequential behaviors an agent cannot infer from readOnlyHint/destructiveHint/idempotentHint.

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 action, then cost, then the confirmation flow, then what the card shows and what comes next. It is dense but nearly every clause carries actionable information; the one soft spot is that the card-display sentence is longer than it needs to be.

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?

An output schema exists, so return values need no explanation, and the description covers cost, confirmation flow and downstream wiring for a tool with nested objects and 5 parameters. What is missing is any statement about the businessContext object and about what a failed or refunded batch leaves behind, which matters given destructiveHint=true.

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 60%, so the schema documents prompt, variant and approvalId, while directions and businessContext items are undocumented there. The description helps by saying to pass 'the brief and a name and short summary for each direction', which maps onto prompt and directions.title/direction, but businessContext (kind, businessKind, offering) is never explained and the retry/quote semantics of variant and approvalId are left entirely to the schema.

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?

States a specific verb and resource: 'Prepare three rough draft website design directions for the person's business from approved design references', plus what must be passed in. It names downstream siblings (iter0_confirm_paid_action, iter0_create_site) so the agent can see where this sits in the flow, but it never contrasts the tool with iter0_design_layout, the closest-sounding sibling.

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?

Gives real procedural context: this is the batch-of-three draft step, a paid request first returns a quote and starts nothing, and work begins only when the person confirms in the card or in chat. That is clear when-to-use guidance, but there is no explicit exclusion such as when to pick iter0_design_layout or iter0_get_design_set_status instead.

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