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

Annotations declare readOnlyHint=true, so safety is covered. Beyond that the description adds genuinely useful behavior: large metrics are compacted with daily series collapsed to summaries, the trimmed content is enumerated in metricsTrimmed, and findings are never trimmed. That compaction/trimming contract is not derivable from the schema or annotations.

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?

Two sentences, no filler, with the return contents front-loaded before the compaction caveat. Dense but every clause carries payload information; only the long enumeration slightly tests readability.

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 correctly carries the burden of describing the return shape, and it does so thoroughly including the metricsTrimmed field. The residual gap is minor: it doesn't note that a runId comes from list_runs, which is where the agent would naturally look.

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?

Only one parameter (runId) with 100% schema description coverage, so the schema already documents it fully. The description adds no format, source, or lookup guidance for the id, so baseline 3 applies.

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 ('one run in detail') and enumerates the payload (status, errors, steps, comparisons, metrics, dashboard link). This implicitly distinguishes it from list_runs, but it never names that sibling explicitly, so differentiation is left to inference.

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: the agent must infer that this is the detail view reached after list_runs surfaces a runId. There is no explicit when-to-use, no prerequisite (e.g., 'requires a runId from list_runs'), and no stated exclusion for the listing tool.

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