list_cloudflow_flow_runs

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond them: newest-first ordering, default inclusion of test runs, pagination semantics including the stop condition, and an explicit statement of what is NOT returned (per-node detail). This is richer behavioral disclosure than most sibling definitions provide.

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?

The description is longer than average but nearly every sentence earns its place: ordering, mode default, sibling routing, and pagination instructions are all load-bearing. The only waste is the vague opener 'Manage CloudFlow,' which repeats the tool's domain without adding decision-relevant information. Front-loading the core result before the pagination details is good structure.

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?

For a 5-parameter paginated list tool with no output schema, the description covers the critical operational details: what is returned, ordering, default mode, pagination chaining, and where to go for deeper detail. Gaps remain: the shape of a run object is never described (though no output schema exists), and maxResults behavior (default page size) is not clarified. The pagination stop-condition guidance is the kind of completeness that prevents agent loops.

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 only 20% (only customerContext documented), so the description carries a high burden. It explains mode ('separate test runs from production ones — test runs are included by default') and pageToken ('passing the response's pageToken value as the pageToken parameter'), which are the two behaviorally meaningful parameters. However, maxResults is never mentioned despite being undocumented in the schema — the agent must infer its role purely from the schema min/max.

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 states a specific verb+resource: 'Returns a flow's runs, newest first.' It also explicitly distinguishes itself from the single-run sibling by noting 'Per-node detail is not included here; fetch a single run...' — an agent can tell this tool apart from get_cloudflow_flow_run and list_cloudflows without opening their schemas. The opening 'Manage CloudFlow' is filler, but the substantive content is precise.

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?

The description explicitly names the alternative and the condition that selects it: 'Per-node detail is not included here; fetch a single run to read what each node consumed and produced.' It also gives concrete usage guidance for pagination ('call again passing the response's pageToken value... Stop once the response has no pageToken') and for the mode parameter ('test runs are included by default'). Nothing is left to inference.

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