get_agent_usage

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

With no annotations, the description carries full burden. It discloses the metrics returned and parameter semantics, but lacks details on output format, pagination, or authorization requirements. Adequate but not comprehensive.

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?

Well-structured: purpose, uniqueness, example questions, then parameters. Slightly long due to question list, but each sentence adds value. Front-loaded with essential information.

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?

Covers purpose, metrics, parameters, and use cases. Lacks explicit output schema description, but output can be inferred. Adequate for tool selection and invocation given 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?

Schema coverage is 0%, but the description fully compensates by explaining each parameter: period with examples ('7d', '30d', 'mtd'), agent_id, team, model as optional filters. Adds meaning beyond the 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 clearly states the verb 'Return' and resource 'LLM inference usage aggregated by agent' with specific metrics (token consumption, GPU cost, request counts). It distinguishes from siblings by claiming to be the only tool bridging agent-level identity with GPU-level cost, which is supported by typical questions. No tautology.

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 provides explicit use cases (e.g., 'which AI agents are consuming the most inference resources') and typical questions. It implicitly differentiates from alternatives by stating uniqueness, but does not list specific siblings or when not to use. Clear context, no exclusions.

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