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

With no annotations, the description carries the full behavioral burden. It communicates the aggregate scope and optional breakdown behavior, but does not disclose response shape, pagination, units, or limitations (e.g., no filtering by user/workspace). Core behavior is clear, but deeper traits are missing.

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?

Two sentences with zero filler. The first sentence front-loads the action and output metrics; the second packages grouping instructions and use-case examples efficiently.

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 2-parameter, 0-required tool with no output schema, the description covers what, how, and why: all returned metrics are listed and the optional grouping is explained. It doesn't specify the exact response structure for grouped results or units, but these are minor given the schema's thorough parameter documentation.

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%, and the schema already fully documents days (default 7, 1-90) and group_by (enum, omit for aggregate). The description adds only minimal extra meaning by framing group_by as per-model/per-provider breakdowns, which largely restates the schema. Baseline 3 is appropriate.

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 a specific verb and resource ('Get AI/LLM usage summary') and enumerates exact metrics returned: total cost, tokens, calls, errors, and latency. It clearly distinguishes itself from siblings like get_ai_calls (individual calls) and get_ai_cost_trend (trend analysis) by presenting itself as the aggregate summary tool.

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 concrete trigger questions ('how much am I spending on AI?', 'which model has the most errors?') that tell an agent when to select this tool. However, it never explicitly names alternatives or states when NOT to use it, so some ambiguity remains against similar siblings like get_cost_summary.

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