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

Beyond the readOnly/non-destructive annotations, the description discloses ordering (newest first), the exact fields returned, that single-call lookup includes the charge's final state and any async job, and precise auth requirements (requests:read, default behavior for unrestricted vs. product-line-limited keys). It also notes the tool is free, which is meaningful operational context.

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 front-loaded with the return fields and lookup mode, and every clause is relevant. It is somewhat dense and the permission explanation is verbose, but it contains no filler or repetition.

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?

With no output schema, the description fully describes the return fields and ordering, covers both list and single-lookup modes, and explains the permission model and cost. Nothing essential for correct invocation is missing, and the schema handles limit/offset details.

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 description coverage is already 100%, so baseline is 3. The description adds genuine meaning for request_id (where it comes from: request_id / X-Request-Id of any call, and what it returns: charge state and async job), though it adds little beyond the schema for limit, offset, and failed_only.

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 states a specific resource and scope: the account's call records, with enumerated fields (request_id, capability, status code, latency, rows returned, charged flag, amount). It also distinguishes two modes (listing vs. single-call lookup via request_id) and names the charge/refund and async-job context, making it clearly separable from siblings like usage or billing.

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?

It gives clear usage contexts: pass request_id to look up one call, use failed_only=true to list failures only, and otherwise list records. It does not, however, name alternative tools or explicitly state when not to use this tool versus everyinfra_usage or everyinfra_billing.

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