Workload

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

readOnlyHint=true is already provided, so the safety profile is covered by annotations, and the description does not contradict it (opening a UI view is read-only). It usefully adds that the result carries a browser_url to be rendered as a clickable link, which is real behavioral value beyond the annotations, but it states nothing about session/auth behavior or what the view returns. The phrasing 'run them against the cluster' could be misread as a consuming action, though it describes the view's features rather than this tool's effect.

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 action is front-loaded in the first two words, which is good, but the body spends several clauses describing the view's feature set and then repeats output-rendering instructions in a second block, padding a one-parameter navigation tool. The Args and browser_url sections each carry some value but the middle sentence does little work for selecting or calling this tool.

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 appropriately mentions the browser_url return, and readOnlyHint covers safety. However, against a dense sibling set of workload_* tools it fails to establish where this entry point sits relative to workload_run/workload_compare, leaving the main ambiguity an agent would face unresolved.

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% for the single 'name' parameter, so the description must carry the meaning. It does document it as 'Workload to select (optional)', clarifying the optionality and purpose, but adds no format, lookup source, or behavior when omitted, so it only partially compensates for the coverage gap.

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 opening clause 'Open the Workload view' is a specific verb+resource, but the rest of the description enumerates capabilities (define statements, run with N connections, compare runs) that are actually performed by the many workload_* siblings, without drawing any line between them. An agent could reasonably conclude this tool itself runs and compares workloads rather than just opening the view, so the purpose is muddied rather than sharpened.

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 implies a use case ('before and after a new sort key or index'), which gives an agent a rough sense of when the Workload view is relevant. However, it never states when to call this tool versus workload_run, workload_compare, workload_overview, workload_define, or the generic app_page sibling, so the routing guidance is only inferred.

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