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

With no annotations, the description must fully disclose behavioral effects. It mentions the payout split (90%/10%), but omits critical details such as whether the action is irreversible, whether it requires sufficient escrow balance, failure conditions, or any side effects beyond fund distribution.

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 a single, concise sentence that conveys the core action and business outcome. It is front-loaded and free of fluff, though it could have incorporated parameter guidance without becoming overly long.

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 financial transaction with no annotations and no output schema, the description lacks essential context about preconditions, response behavior, error cases, or whether the action can be reversed. The payout split is useful but insufficient for safe invocation.

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?

The single parameter campaignId has 0% schema description coverage, and the tool description does not explicitly mention 'campaignId' or explain that it identifies the campaign to confirm. The description only implies the campaign context, leaving the parameter's role to inference.

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 action: 'Advertiser releases escrow after confirming ad delivery/attribution.' This names the verb (releases escrow) and the resource (ad delivery/attribution), and distinguishes it from siblings like deliver_ad (publisher-side) and report_conversion (attribution reporting).

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 phrase 'after confirming ad delivery/attribution' implies a precondition but provides no explicit guidance on when to use this tool compared to alternatives. There is no mention of exclusions or related tools, leaving the usage context somewhat vague.

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