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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structure. The description adds genuinely non-obvious behavior beyond that: newest-first ordering, a 10-per-page default, and most importantly that the API only returns builds from the last 90 days so the reported total can exceed what is pageable. That retention/consistency caveat is exactly the kind of disclosure annotations cannot convey.

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?

Three sentences, no filler, and the ordering/default-page-size facts are front-loaded before the caveat. Every sentence carries distinct information: what is listed, how to page, and the retention limitation.

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?

There is no output schema, so the description carries the burden of describing returns, and it does: ordering, page size, and the behavior of the total relative to the pageable set. Combined with full schema coverage on all three parameters and safe-read annotations, an agent has everything needed to call this 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 limit and offset are already documented and the baseline would be 3. The description goes slightly beyond the schema by explaining the total-vs-pageable interaction that arises from the 90-day truncation, which affects how an agent should interpret paging results. The status parameter is not addressed at all in the description.

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?

The description opens with a specific verb+resource ('Lists mobile app automation builds') plus ordering ('newest first') and default page size, which is far more than a restated title. It does not, however, name or implicitly distinguish itself from nearby siblings such as listMobileSessions, listUploadedApps, or listHyperExecuteJobs, leaving the resource name alone to do the disambiguation.

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 explicit when-to-use / when-not-to-use statement or reference to an alternative tool for retrieving build data, so tool selection is left to inference from the resource name. The description does give practical usage mechanics (paging with limit/offset) and a conditional caveat about the 90-day window, which is useful but not selection guidance.

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