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

Goes well beyond the annotations with real behavioral facts: screenshot/baseline/diff links expire after 10 minutes, whether a comparison decision can be undone, ignored findings are marked, noFix findings carry an explanation, and metrics (never findings) are compacted with omissions listed in metricsTrimmed. These are exactly the operational details an agent cannot get from readOnlyHint/destructiveHint.

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-loads 'One run in detail', but the rest is a single run-on sentence with deeply nested parentheticals that make the key facts (link expiry, metrics trimming) hard to scan. Information-dense yet structurally hard to parse.

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 return-value burden and does so thoroughly: findings keys for ignore_finding, comparisonId, link expiry, undoability, metrics trimming. It stops short of covering error/not-found behavior or navigation hints to adjacent tools.

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% and there is a single required runId, so the schema fully documents the parameter. The description adds nothing about runId format or source, so the 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+resource ('Get run details' / 'One run in detail') and enumerates the concrete payload (status, errors/warnings, steps, comparisons, metrics, proposed fix). The phrase 'One run' implicitly contrasts with list_runs, but the description never explicitly names that sibling to sharpen the distinction.

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 'use this when' guidance, no exclusions, and no named alternatives (e.g., list_runs for an overview, get_fix_prompt for fix details). Usage is only inferable from the singular 'One run' phrasing.

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