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

With no annotations provided, the description fully discloses key behaviors: returns 202 immediately, background scoring, transcript never stored, only scorecard and safe metadata kept, and idempotent handling via externalId. This is rich, operationally critical information.

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 concise sentences, each packed with distinct information: purpose, async behavior, data handling, and idempotency tip. No fluff, front-loaded with the core action.

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 6-param tool with no output schema, the description covers the essential operational aspects: async return, background processing, data retention, and idempotency. It doesn't describe response body or error cases, but covers the most critical context for correct 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?

Schema coverage is 100%, so baseline is 3. The description adds meaningful context beyond schema, especially for externalId (idempotency guarantee) and transcript (scored in flight, never stored), which enhances the agent's understanding of how these params affect behavior.

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 a specific action: 'Send one completed PRODUCTION call to a monitor to be scored.' This distinguishes it from sibling tools like run_test or run_demo by emphasizing production calls and the ingestion aspect.

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 clear context: it's for completed production calls and explains the async behavior and idempotency via externalId. It doesn't explicitly name alternatives, but the production qualifier and 'one completed call' guide appropriate use.

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