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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding real behavior: only ONE group_by dimension at a time, the remaining dimensions act as filters, and the response always includes this month's run rate and forecast regardless of range. It does not mention the 20-row default cap or row limits.

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?

A single front-loaded sentence, 'AI spend for a date range', followed by a colon-delimited enumeration of what comes back. Dense but zero waste; it would read slightly better split into purpose and output clauses.

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?

An output schema exists, so return values need no explanation, and the readOnly annotations cover safety. However, with 11 all-optional parameters and 27% schema coverage, the description omits default behavior — what range you get with no dates and what `limit` truncates — which an agent needs to call this 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 only 27%, so the description must carry weight and it does explain the most subtle rule — group_by takes one dimension while the others filter, meaning the grouped dimension is excluded from filtering. But it leaves `limit` (default 20, max 100) and the default date range when start/end are omitted completely undocumented.

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 resource and scope: 'AI spend for a date range' with totals, an optional single-dimension breakdown, filters, and run rate/forecast. That is far more than a restatement of the name, but it never names a sibling (get_customer_cost, get_margin, compare_models) to mark where its territory ends.

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?

Usage is implied rather than stated: 'an optional breakdown by one dimension, filters on the others' tells the agent how to shape a call, but there is no explicit when-to-use-this-instead-of-get_customer_cost or get_margin guidance, and no exclusions.

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