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

Beyond annotations (readOnlyHint/idempotent/destructive false), the description discloses a Last Price credential requirement, a claim-workspace precondition with the exact failure mode (sandbox self-registered keys get 403 until claimed), and the default time window. That is meaningful operational context; only rate limits/pagination-ish concerns for the daily series are unmentioned.

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?

One tight paragraph: purpose and return shape first, then period control, then safety, then prerequisites, ordered by what an agent needs before calling. No filler sentences and nothing repeated from the annotations beyond a single confirming 'Read-only'.

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 two-parameter read tool with no output schema, it covers what comes back at a summary level, the default window, auth and workspace prerequisites, and the 403 failure path. Remaining gaps (timezone semantics, response shape details) are minor but real.

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 already 100%, so the baseline is 3; the description adds value by stating that both parameters are optional and that omitting them yields month-to-date, which the schema does not say. It still does not clarify timezone or inclusive/exclusive boundary handling for the date-time range.

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 states a specific resource (model call costs for the workspace) and names the breakdown dimensions (totals, own provider key vs platform key, daily series). It is clear on its own, but never distinguishes itself from near-identical siblings such as get_usage, get_usage_breakdown, get_cost_analytics, or list_llm_usage_events.

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 one concrete usage cue (default is the current month so far; pass start_date/end_date to change the period) and implicitly frames the tool as an aggregate cost view. However, it never says when to prefer it over get_usage_breakdown or list_llm_usage_events for event-level detail, so the agent must guess among siblings.

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