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

Annotations already declare readOnly=true, idempotent=true, and openWorld=true, so safety is largely covered; 'Starts no work' merely echoes that. The description does add one genuinely useful behavioral caveat, 'Phases that were not recorded stay unmeasured,' which tells the agent results can have gaps — but says nothing about latency, cost, or how 'recent runs' are bounded.

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?

Front-loaded with the core capability and only three short sentences; nothing is padded. It does, however, almost verbatim duplicate the title, so the sentence earns less than it could.

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 usefully enumerates what the report contains (medians, p90s, recent runs), which is the right kind of compensation. But it leaves the parameter surface entirely unexplained and doesn't clarify the reporting window or scope, so an agent still has to infer quite a bit.

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 0% across three parameters, and the description supplies no meaning for company, environment, or days. The 7/30/90 day window in particular is undiscoverable without opening the schema, and even there it is 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?

States a specific verb (Read) and a well-defined resource: timing of approved agent runs, broken into approval-to-start, startup/work phases, and per-step metrics with medians and p90s. This is much more precise than the bare name, but it never distinguishes itself from adjacent read tools such as summer_runs_list or summer_reports_service_metrics.

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 when-to-use guidance, no named alternative, and no exclusion criteria. The only scoping statement is 'Starts no work,' which clarifies effect but not selection between this report and the other report/run tools.

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