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

Annotations cover the basic profile (write, not idempotent, not destructive, closed-world), and the description adds genuinely useful behavior beyond them: a human (Jon) reviews the request, the outcome arrives as a proof or quote on a private reply link, and no charge occurs on this call. It doesn't mention the callback_url follow-up flow, but the core async human-in-the-loop contract is disclosed.

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?

Four short sentences, front-loaded with the action and audience, then the workflow and the cost reassurance. Each sentence earns its place, though the opening 'Ask Corbah to...' phrasing is slightly indirect for a tool named commission_design.

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 an 8-parameter, no-output-schema tool, the description covers what the call does, who handles it, how the response is delivered, and that it's free. It leaves the callback_url notification path and the budget parameter unexplained, which the schema partially covers (88% coverage), so the picture is nearly complete.

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 description coverage is 88%, so the schema already documents brief, items, deadline, for_whom, reply_to, and image_urls. The description only reinforces that the brief can carry 'any detail you have' and does not clarify the undocumented budget field or how reply_to interacts with the private reply link, so it adds little beyond 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: asking Corbah to design custom cycling kit, with concrete use cases (club, team, event, ride, person, idea). It is clearly distinguishable from generic siblings like ask_corbah or send_message by its design-commission framing, though it never explicitly contrasts itself with them.

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 implies when to use it ('Describe what you want in any detail you have') and the use-case list signals the intended scenario, but there is no explicit when-not guidance or named alternative for someone who just wants a general question answered (e.g. ask_corbah).

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