Get Project Flow Metrics

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

Beyond readOnly/idempotent annotations, it reveals the cost model ('roughly one API request per sampled task'), the sampling bound (max_tasks hard cap 100), server-wide request budget, and that the response reports sampling coverage. It also notes the statistical treatment of cycle time (mean as secondary due to right skew), which is useful behavioral context.

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?

The description is compact but rich: main action first, then return list, then cost warning, then usage questions. Each sentence adds distinct information without fluff, making it appropriately sized and front-loaded.

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 complex analytics tool with no output schema, it conveys the full return payload (percentiles, dwell times, throughput, reschedule stats, offender lists with permalinks), the cost/sampling behavior, and when to apply it. Combined with fully-described parameters, it is complete.

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?

The schema already provides 100% parameter coverage, so the description doesn't need to carry semantics. The only extra value is reiterating that max_tasks bounds the cost, but that's already in the parameter description. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Compute delivery-flow statistics for a project by replaying the activity stream of its recently-completed tasks.' It enumerates concrete outputs (cycle-time/lead-time percentiles, dwell times, throughput) and the questions it answers ('where does work get stuck?'), clearly distinguishing it from simple getter siblings.

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 provides explicit use cases ('Use this to answer...') and cost guidance (EXPENSIVE: costs one API request per sampled task, bounded by max_tasks). It does not name alternative tools for exclusions, but the context is clear, so it earns a 4 rather than a 5.

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