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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world call, so the safety profile is covered. The description adds real behavioral context beyond that: unit conversions for duration/queue/cost, what a missing costUnits means, that a null result for a revision signals changed data, and that filters follow GitHub status semantics.

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?

It is a single dense block front-loaded with purpose, then a stream of field and filter semantics. Every sentence carries information, but a few simply echo the schema (timestamps in epoch milliseconds, omit revision), so it is efficient rather than maximally tight.

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?

Although an output schema exists, the description names the aggregate fields an agent must combine (durationSum/durationCount, queueSum/queueCount) and explains the units and the cost-availability edge case, which is exactly what is needed to interpret the result. Combined with the 366-day range limit in the schema, an agent has everything required to call and read this tool 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 description coverage is 100%, so the baseline is 3. The description mostly restates schema facts (epoch milliseconds, omit revision for current data, omit repositoryId for all repos) but does add meaning the schema lacks — notably that filters map to GitHub status and that the repositoryId choice should not be emulated by enumerating repositories.

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 opening sentence names a specific verb and resource set — job duration, queue time, success rate and cost — scoped to a workspace and time range, so the agent knows exactly what this returns. It also implicitly separates itself from a per-repository enumeration approach, though it never names a sibling tool (e.g. get_usage or get_dashboard) that could be confused with it.

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?

Clear conditional guidance is given for the key decision points: omit repositoryId for workspace totals, supply it only to narrow scope, and explicitly 'Do not enumerate repositories to calculate workspace totals.' It also states when to omit revision and how to pick a status filter. It stops short of naming alternative sibling tools for adjacent questions, so it is not a full 5.

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