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

Annotations already declare readOnly/destructive=false, so the bar is lower; the description still adds real value by disclosing the required 'requests:read' permission, how default vs product-line-limited keys differ, and that lookups include the charge's final state and any async job. It stops short of describing pagination behavior beyond what the schema shows.

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?

Front-loads purpose and the two modes before the permission note; every sentence carries information. The permission explanation is somewhat long but is actionable for an agent that might otherwise hit an auth failure.

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 enumerates the returned fields, both lookup modes, the charge-state semantics, and the auth prerequisite, leaving nothing an agent needs to call it correctly.

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 the baseline is 3, but the description adds meaning: it clarifies that request_id is the X-Request-Id of any call and that the other params are ignored when it's given, plus what failed_only filters. This genuinely enriches the schema 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?

States a specific verb and resource ('the account's call records, newest first') and enumerates the returned fields, so an agent knows exactly what this yields versus sibling tools like everyinfra_call_api or everyinfra_list_capabilities.

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?

Clearly explains the two modes: passing request_id selects a single-call lookup, and failed_only=true restricts to failures. It gives clear context for each path but does not explicitly name a competing sibling or state when not to use this tool.

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