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

Beyond the readOnly/idempotent annotations, the description explains key runtime behaviors: only cache misses that reached the origin, results ordered newest-first, default mode is live serves, previews=true switches to editor-preview history, and history is retained for about two weeks. This gives a clear model of what the call will return and how to interpret results.

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 typical but every sentence adds distinct value: purpose, result contents, relationship to related tools, scope, retention, and default behavior. It is front-loaded with the core purpose and the additional details are tightly packed without redundancy.

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?

Given the schema and annotations, the description fills all remaining gaps: it explains the difference from other run-listing tools, what each item contains, how to access further run details, retention limits, and how to switch preview modes. The output schema is present, so return values do not need elaboration.

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?

The schema already covers all parameters (100% coverage), and the description adds crucial meaning: slug and endpoint_id are alternatives, previews defaults to false, page_token comes from a previous response's next_page_token, and page_size limits the number of runs returned. This clarifies how to use each parameter without ambiguity.

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 clearly states a specific verb ('List'), resource ('dynamic endpoint's recent EXECUTIONS'), and ordering ('newest-first'). It also provides a concrete use case ('the place to look when a live page is broken') and distinguishes from related tools by focusing on dynamic endpoint runs and their resolved request paths.

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 gives explicit guidance on when to use (when a live page is broken), what is excluded (cache hits, traffic, previews by default), retention ('about two weeks'), and how to switch to preview history ('pass previews=true'). It also points to related tools for deeper investigation (get_workflow_run / get_workflow_run_traces).

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