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

With annotations indicating readOnlyHint=false, the description adds critical context: the tool is a paid operation with a non-refundable fee plus refundable bond, requires payment proof, and cannot succeed on blind retry. It also mentions that the operation is irreversible in terms of cost (non-refundable fee). This goes beyond the basic mutation flag and explains the payment and retry behavior, but it doesn't detail side effects like whether the intent becomes visible immediately or duration limits beyond schema.

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 concise but packed with essential information: what the tool does, the payment requirement, the precise call flow (check payment, pay, retry), and a caution to publish only with agreement. It is front-loaded with the core purpose and the paid nature, then the procedural details. No redundant sentences; every one adds value.

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?

Given the tool's complexity (payment, retry flow, user agreement), the description covers the essential steps: check payment status, handle payment_required, retry. It also warns about blind retries. However, it doesn't specify what the response looks like, but there is no output schema, so the agent might want to know if it returns an ID or success indicator. Also, it doesn't mention potential errors for rejected content, but the schema mentions rejection. Overall, it's fairly complete for a payment-gated publish tool.

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 schema documents all parameters well. The description adds value by clarifying the payment parameter: it says to attach proof after payment, and implies the payment field is how to attach it, but it doesn't explicitly name 'payment' field. It also emphasizes the title field as 'from the user's side' and content rules, which reinforces schema. However, it doesn't add extra meaning to 'city' or 'window_minutes' beyond what schema says. Given 100% coverage, baseline is 3, but the description's hint about payment proof and retry adds a bit more, so 4 is justified.

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 clearly states the verb 'publish' and the resource 'coordination intent', with specific constraints (one city, bounded window, person you act for) and the paid nature. It distinguishes from siblings like 'reciprocate_intent' and 'report_intent' by explicitly framing this as the act of announcing an intent. The title confirms it is a paid publishing action, which is unambiguous.

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 provides explicit guidance: call `get_payment_status` first, if payment is required pay then retry, and a blind retry cannot succeed. It also advises to publish only with user's agreement. This tells the agent exactly when and how to use the tool, including preconditions and payment flow, which is more than just context.

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