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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuinely new behavioral context beyond the schema: the default lookback of 30 days and the 90-day maximum range constraint, which an agent would otherwise not know.

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 dense sentence that front-loads the scope ('time-bucketed ... analytics') before the metric list, default window and backend reference. Every clause carries information, though the trailing service/method identifier is low-value to an agent.

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 compensates by summarizing the return shape: totals plus hourly or daily buckets across named metrics. No authentication or permissions context is given, but for a read-only analytics call the picture is largely complete for correct invocation.

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% with per-parameter descriptions, so the baseline is 3. The description restates the bucket granularity and date defaults but adds no filter-combination semantics or format details beyond what the schema already documents.

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 verb and resource ('Get time-bucketed GitHub Actions analytics for Depot runners') and enumerates the exact metrics returned (job counts by outcome, failure rate, elapsed/billable seconds, average duration). This clearly separates it from siblings like depot_gha_list_jobs or depot_gha_search_logs, which retrieve records rather than aggregates.

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 default window (last 30 days, max 90) tells the agent what happens when no time filter is supplied, which is useful context. However, it never says when to prefer this aggregate tool over record-level siblings such as depot_gha_list_jobs or depot_ci_list_runs, so the routing decision is left to inference.

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