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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real value on top: a 30-day retention window, a newest-first ordering guarantee, and a metadata-only payload contract. It does not describe pagination behaviour beyond the limit cap of 100, which is a minor gap given the safety profile is already declared.

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?

A single sentence carries scope, ordering, the optional filter, the returned field set, and the metadata boundary, with the parenthetical used efficiently. Nothing is padded and the most decision-relevant facts come first.

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 usefully enumerates the return fields and the metadata-only boundary, so an agent knows what to expect. It is close to complete for a two-parameter list tool; only pagination behaviour past the limit cap is left unspecified.

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 coverage is 100%, so both parameters are already documented, and the description only reinforces that workflow_id is optional (omit to list across workflows). It adds no syntax or formatting detail for workflow_id or limit beyond the schema, so the baseline of 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?

The description gives a specific verb and resource ("Lists recent runs") plus scope (last 30 days, newest first) and an optional workflow filter, and enumerates the fields returned. It implicitly distinguishes itself from get_run by stating "Metadata only", though it never names that sibling explicitly.

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 implied rather than stated: "optionally for one workflow" tells the agent the filter can be omitted to span all workflows, and "Metadata only" hints that detail work belongs elsewhere. There is no explicit when-not guidance and no sibling such as get_run or list_waits is named as the alternative.

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