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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful context beyond that: the default window is 24h and the response contains aggregate punctuality metrics rather than raw records. It says nothing about cost, latency, or how the aggregates behave for jobs with no runs, so 3 is appropriate.

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 front-loaded sentence listing the metrics and default, followed by a compact REST mapping. Nothing is padded, though the parenthetical REST hint is low value for an MCP caller.

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 carries the burden of explaining return values and does so by naming the metrics. Missing details are minor: units and formatting for p50/p95 delay and whether the response includes the effective window used.

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 67%: job_id and management_token are documented in the schema, but the window enum carries no per-value description. The description compensates by stating the default window is 24h, which is genuinely new meaning. It adds nothing about the effect of window on aggregation granularity or token requirements beyond what the schema states.

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 names the exact metrics returned (on-time rate, p50/p95 first-attempt delay, success rate) and scopes them to a job over a window, which is far more informative than the name 'get_stats' alone and separates it from get_job, get_run, and get_deliveries. It doesn't explicitly say 'for a given job', but the REST path '/v1/jobs/{id}/stats' and the required job_id make the target unambiguous.

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?

There is no statement of when to choose this over get_deliveries, get_run, or get_job, nor any prerequisite or exclusion. An agent must infer that 'get_stats' is for aggregate performance metrics rather than per-delivery detail purely from the metric names.

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