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

With only readOnlyHint available, the description carries the real behavioral load: it discloses data granularity (hourly, daily after 2 days, monthly after 40 days), the minimum range constraint, and the non-obvious rule that uptime is omitted when grouping. These are genuinely useful facts not derivable from the annotations or schema.

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?

Return contents are front-loaded, followed by the grouping option, then the granularity/constraint caveats. Every sentence adds distinct information with no repetition.

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?

No output schema exists, but the description enumerates the response fields and their granularity, covers the grouping caveat, and states the range precondition. An agent has everything needed to call and interpret the result correctly.

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 100%, so the baseline is 3, but the description adds meaning: it clarifies the group enum ('time' vs 'host', with host glossed as monitoring location) and that grouping suppresses uptime. It does not re-explain token/from/to formats, but the schema already does that well.

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 and resource ('Get aggregated metrics for one check') and enumerates exactly what is returned: uptime, apdex, timings, request counts. This clearly distinguishes it from sibling updown_get_check, which returns check config rather than 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?

Gives the operating context (over a time range, optionally grouped) and the hard precondition that the range must span at least one hour. It does not explicitly route the agent between this and updown_get_check/find_problems, so it stops short of a 5.

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