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

Annotations already establish readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds what the read returns (phase timings, success rates, throughput) but says nothing about time-window scoping, aggregation cost, or freshness of the statistics, which are the traits that actually matter for an aggregate stats call.

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 sentence with the verb, resource, and scope front-loaded; every clause (metrics enumerated) earns its place and nothing is padded.

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 parameters, no output schema, and read-only annotations, the description is nearly sufficient: it tells the agent what the returned statistics cover. It stops short of noting the time window or whether the aggregates are live versus periodically computed, which matters for interpretation.

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 tool takes zero parameters, so there are no parameter semantics for the description to supplement; the baseline of 4 applies. Note that the lack of any time-range or filter parameter means the aggregation scope is entirely fixed and undocumented.

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?

Specific verb ('Get') plus resource ('aggregate pipeline telemetry statistics') with a clear scope qualifier ('across all jobs'), and it enumerates the metric families returned (phase timings, success rates, throughput). It does not name siblings, but the 'all jobs' aggregate scope implicitly distinguishes it from per-job tools like get_job_telemetry.

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?

Usage is only implied by the scope phrase 'across all jobs'; there is no explicit statement of when to prefer this over get_job_telemetry, get_active_telemetry, get_telemetry_logs, or system_telemetry. In a sibling list this crowded, that omission is a real gap.

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