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

Annotations already declare destructiveHint=true, and the description goes beyond that by explaining the actual billing consequence: 'deducts/credits a feature balance'. This adds meaningful behavioral context for a mutation tool. The description is consistent with the annotation and adds the either/or key constraint, though it doesn't discuss reversibility or retry behavior.

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 only two sentences, yet every part carries load: mutation status, balance effect, parameter exclusivity, and the underlying API endpoint. No filler or redundant restatement of the tool name. It is front-loaded with the most important behavioral signal.

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 destructive 8-parameter tool with no output schema, the description supplies the critical side-effect and the one genuinely ambiguous invocation rule, while the schema covers all parameter details. It could add more on prerequisites, idempotency usage, or postconditions, but an agent can correctly invoke the tool with the information provided.

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?

Input schema coverage is 100%, so the schema already fully describes all eight parameters including value, timestamp, entity_id, and idempotencyKey. The description adds a useful cross-parameter rule for feature_id/event_name and the credit/debit interpretation of value, but most parameter semantics are already carried by the schema. This is a solid baseline case.

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 opens with 'MUTATES Autumn billing data — records a usage event (deducts/credits a feature balance)', which names a concrete verb, resource, and effect. This clearly distinguishes the tool from the many read/list siblings while also identifying the specific billing operation. The endpoint reference reinforces what the tool does.

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 gives a helpful parameter-selection rule ('Provide EITHER feature_id OR event_name') and implies it is the tool for usage events, but it never explicitly contrasts track_usage with siblings such as autumn_request or states when not to use it. Usage context is implied rather than formally differentiated from alternatives.

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