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

Since no annotations are provided, the description carries the full burden. It discloses the return values (success, impression_id, earnings) and implies a write operation with financial impact ('earnings credited'), giving the agent an accurate model of side effects. It does not cover auth or idempotency, but the core behavior and key consequences are clear.

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 well-structured with WHEN TO USE, RETURNS, and EXAMPLE sections that each serve a clear purpose. It is concise, with no redundant content, and the opening sentence immediately states what the tool does.

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 single-impression write tool with no output schema, the description fully covers return values, usage context, and an example, which is sufficient for most agent interactions. It doesn't explain the metadata parameter in depth, but the schema covers it, and the tool's complexity is moderate, so overall it's complete enough.

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 input schema already describes all 5 parameters with 100% coverage, so the baseline is 3. The description adds no additional parameter meaning; the example merely uses fingerprint, ad_id, and duration_seconds without explaining them beyond the schema. Thus, it doesn't compensate beyond the schema's descriptions.

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 starts with 'Record a single ad impression from a device', clearly identifying the verb (record), resource (ad impression), and scope (single, from a device). It explicitly differentiates from batch_impressions by saying 'Single impression events (for batch, use batch_impressions)', making it easy to select among siblings.

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?

A dedicated 'WHEN TO USE' section lists explicit scenarios such as 'Reporting that an ad was displayed on a device' and 'Recording impression with detailed metadata'. It also provides an explicit alternative: 'for batch, use batch_impressions', which is exactly the kind of guidance needed for tool selection.

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