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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile; the description adds substantial behavior beyond that: only cache MISSES reaching the origin appear, history is kept ~two weeks, ordering is newest-first, and items expose the failure message the public URL hides behind a 500. No contradiction with annotations.

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?

Five dense sentences, each carrying a distinct fact: scope+ordering+use case, item contents, run_id resolution, data scoping+retention, and the previews default. The primary purpose is front-loaded; slightly long, but every sentence earns its place given the tool's behavioral nuance.

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?

An output schema is present, so return-value format does not need explaining, and the description covers the non-obvious context: cache-miss-only data, two-week retention, live-vs-preview default, and the path to step-level traces. The only gap is an explicit sibling contrast with list_runs, which is minor given the otherwise clear scoping.

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 the schema already documents all five parameters; baseline 3 applies. The description adds modest reinforcement for previews ('Defaults to live serves') and gives meaning to request_path (an output field) regarding :param values, but adds little new input-parameter semantics beyond what the schema already states.

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?

States a precise verb+resource: 'List a dynamic endpoint's recent EXECUTIONS, newest-first.' It immediately gives the operational use case ('the place to look when a live page is broken') and narrows scope to dynamic endpoints, clearly distinguishing it from generic siblings like list_runs and list_schedule_runs. The live-vs-preview distinction further sharpens exactly what this tool enumerates.

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?

Gives an explicit when-to-use ('the place to look when a live page is broken') and routes follow-up resolution to get_workflow_run / get_workflow_run_traces via run_id. It also instructs when to switch modes ('pass previews=true for the editor-preview history instead') and scopes the data ('renders, not traffic'). It does not explicitly contrast with list_runs, but the scoping is strong enough that the correct selection is clear.

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