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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description adds meaningful behavior: the batch is all-or-nothing, every event needs its own idempotency_key, retries with identical keys are safe, and outcomes are reported as created / duplicate / conflict. It also discloses the auth requirement ('Needs your API key'). This is exactly the kind of context annotations cannot convey.

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?

Three compact sentences, each carrying distinct information: scope/atomicity, idempotency contract, and auth. The most operationally critical constraint (idempotency_key) is front-loaded in the second sentence with no filler.

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-parameter, no-output-schema ingestion tool, the definition covers the essentials: batch limits, atomicity, idempotency, retry safety, result statuses, and auth. It stops short of describing the full response payload or validation-failure behavior, which matters given there is no output schema.

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?

Reported schema coverage is 0% at the top level, but the description compensates only partially: it explains the batch bounds and the critical per-event idempotency_key semantics (same key + same payload = duplicate, same key + different payload = conflict). It says nothing about subscription, value, timestamp, or unique_value requirements, which the agent must infer from the nested 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?

The description names a specific verb and resource ('Record ... usage events'), states the batch size range (1-100), the atomicity model (all-or-nothing), and even the underlying endpoint (POST /api/v1/usage). An agent can immediately distinguish this from siblings like get_meter_rollups or create_meter, which are read/configuration operations.

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?

Usage is implied clearly by the batch/ingestion framing and the retry guidance tells the agent when re-calling is safe. However, it never explicitly states when to prefer this tool over alternatives or what to do if the batch is rejected, leaving the when-to-use decision to inference.

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