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

Beyond the readOnly/idempotent annotations, it discloses authorization failures (FORBIDDEN for member keys widening scope), paywalled sections (money and roster are owner/admin), the response envelope (asOf, timezone, window, units, per-metric definitions), pagination via `page.cursor` with identical arguments, and billing ('one read per call'). That is far more than the annotations carry.

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?

Well front-loaded — purpose first, then explicit WINDOW/SCOPE blocks — and capitalized labels help scanning. The metric-by-metric enumeration (e.g. 'Retasc fee by outcome, labour, and who is behind each bucket') is dense and partly redundant with the `sections` list, but with no output schema it earns most of its space.

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 12-parameter, zero-required, output-schema-less analytics tool, this covers everything an agent needs: what is returned, defaults, timezone and window rules, permission gates, pagination, and cost. Nothing material about invoking it correctly is left unstated.

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% (baseline 3), but the description adds real semantics the schema lacks: it enumerates the valid `sections` values even though the schema has no enum, explains the days-vs-from/to precedence and the bucket-unit behavior per window, and spells out that `maxBars` coarsens and snaps outward rather than refining. It also explains the `bucketFrom`+`bucketTo`+`person` interaction.

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?

Opens with a specific verb+resource framing — every metric the Dash analytics page shows, computed by the same code — and enumerates the actual sections (pipeline, series, fleet, queue, review, money, findings, people) so the agent knows exactly what comes back. Sibling `analytics_issues` is not named, but the breadth described here is unmistakably the org/project overview rather than an issue-level report.

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 an explicit trigger: 'Use it when a human asks how their fleet or project is doing; build the chart yourself from what it returns' — which also tells the agent it produces data, not rendered output. It adds hard preconditions for widening scope (owner/admin or FORBIDDEN) but never names a sibling as the alternative for narrower questions.

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