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

With readOnlyHint=true already declaring the safety profile, the description adds real context: the distinction between 'accepted' (notices counted) and 'limited' (dropped by rate limits), per-period aggregation, and the default of until=now. It stops short of noting limits/order of returned points or any API rate-limit behavior.

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 dense sentences: the output shape and window semantics come first, the motivation and endpoint second. No filler, no repetition of the title.

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?

With no output schema, the description valuably sketches the return structure (parallel arrays) and the time window semantics. It omits how 'limit' truncates or orders the series and what happens for groups with no events in range, which are the remaining gaps for a 6-parameter tool.

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 description coverage is 100%, so since/until/period/limit are already documented in detail by the schema. The description echoes the since/until window and default-now behavior rather than adding syntax or constraints beyond it, matching the baseline for a fully covered 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?

States a precise verb+resource scoped to 'one error group' and names the returned fields (time, accepted, limited), which separates it cleanly from sibling airbrake_get_project_stats. The Airbrake endpoint path is included, removing any ambiguity about what is fetched.

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?

Gives a concrete use case ('see whether an error is spiking or fading'), which is clear guidance. It does not, however, explicitly contrast itself with airbrake_get_project_stats or say when not to use it, so the alternative is left implicit.

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