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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: results are restricted to runs that ended, ordered newest-first, capped at 200 per page, and paginated via a nextCursor that terminates at null.

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?

Dense but front-loaded: purpose and ordering come first, then pagination mechanics. The limit range ('20 by default and 200 at most') restates the schema's default/maximum, a small redundancy in an otherwise waste-free description.

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, yet the description characterizes the returned data (outcome, trigger, failure reason) and the full pagination contract, which is what an agent needs to loop correctly. Coverage is sufficient for a two-parameter list tool; only id provenance is left to the schema.

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?

Although structured schema coverage is reported as 0%, the description conveys the meaning of both optional controls: limit (default 20, max 200) and cursor (feed the previous page's nextCursor, omit for first page). It adds little about the required params.id beyond 'of a report of any type', which the schema itself documents 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 ('the runs of a report of any type that ended'), plus ordering ('newest first') and payload fields ('how each ended, what started it and why it failed'). The 'that ended' scope and list semantics clearly separate it from the singular getReportRun and from listReportSyncs.

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 a concrete triggering question ('why last night's update failed') and explains the pagination loop (pass nextCursor as cursor 'until it is null'). It does not name alternatives such as getReportRun for a single run or listReports for the parent resources, so routing to siblings is left implicit.

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