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

With no annotations, the description carries the full behavioral burden and does so well: default page size of 20, hard cap of 50, newest-first ordering, mutually exclusive period vs from/to, the includeSummary status-filter exception, and the meaning of olderRunsHiddenByPlan and nextOffset. The only unstated behaviors are read-only/safety posture (implicit from the name but not declared) and any rate/permission constraints.

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?

Content is front-loaded: purpose, then ID sourcing, then filters, then row shape, then result envelope. It is dense and semicolon-chained rather than cleanly structured, but nearly every clause conveys operational information (defaults, exclusivity, field meanings) rather than restating the name.

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 supplies the return envelope (versionId, runs, summary, olderRunsHiddenByPlan, nextOffset) and per-row field meanings including hasErrors/errorHandled/terminationReason nuances. For a 12-parameter filtered listing tool with zero annotation coverage, nothing an agent needs to call it or interpret results is missing.

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 0%, so the description must compensate, and it largely does: it enumerates the period enum values, the from/to ISO range form and its exclusivity with period, limit default and max, offset pagination via nextOffset, and the semantics of includeSummary (per-status counts over the same filters, status filter not applied). Only workspaceId is left unexplained, which is a minor omission against 12 parameters.

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?

"List the runs of one flow version, newest first" gives a specific verb, resource, scope, and ordering in one clause. The description immediately separates this tool from get_flow_instance / get_flow_instance_logs by explaining that run instanceKeys from this listing feed those detail tools.

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?

It states preconditions (flowId, versionId, liveVersionId come from list_flows), the default behavior without versionId (LIVE version searched), and the case where versionId is mandatory (no LIVE version exists). It also names the downstream sibling tools to call with each instanceKey, so an agent knows the follow-up path without inference.

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