getGatewayUsage

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

Discloses read-only nature, required linked account (401 error), metadata-only (no transcripts/audio), and what is/isn't metered. Since no annotations exist, description fully covers behavioral traits.

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-loaded with main purpose, returns format explained, then constraints and usage guidelines. Slightly long but every sentence adds new information; no redundancy.

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?

Explains return object shape (window, totals, byModel, creditBalanceUsd), error case (401), and pairing suggestion. No output schema needed; missing only minor details like rate limits or pagination (likely not needed).

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% but description adds value: default value for 'days' (30), bucketing auto-scaling rules, clarifies 'appPackage' as project_install_id. Exceeds baseline 3.

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?

Clearly states verb 'Read' and resource 'account-scoped managed-AI-gateway usage + exact cost'. Distinguishes from siblings by specifying managed-gateway scope and contrasting with direct OpenAI calls.

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?

Explicitly provides USE cases (report spend, dominant model, cost-driven recommendation) and DON'T USE cases (live traces → getEventLog, config changes → setAssistantConfig), with sibling names.

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