workload_run

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

Annotations already establish this is a non-read-only, non-destructive, closed-world mutation. The description adds genuinely useful behavior beyond them: the return value ('Returns the run id'), the single-concurrent-run constraint, and the async-style handoff to workload_status. It does not say whether the call blocks until completion or what happens if a run is already in flight, which would be the remaining gap.

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?

Front-loaded with purpose, constraint, and return value in the first two sentences, then the follow-up tools, then the arg list. The args block partly restates schema field names, but each line adds meaning rather than repeating the schema verbatim, so the size is justified.

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 4-parameter mutation tool with no output schema and no annotation detail, the description supplies purpose, return value, concurrency constraint, and downstream workflow. Missing only edge-case behavior (existing run in flight, blocking vs. async completion) and override units.

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%, so the description carries the full burden, and it does list and gloss all four parameters (name = the workload, label = short run label, duration_s = per-run duration override, concurrency = per-run connection override). It could go further on units/ranges and the fact that duration_s and concurrency are nullable overrides, but the semantics are clearly conveyed.

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 specific verb and resource ('Start a run of a saved workload') with an explicit scope constraint ('one run at a time'), which cleanly separates it from siblings like workload_status, workload_compare, workload_list, and workload_stop.

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 concrete next-step routing ('follow it with workload_status and compare runs with workload_compare') and a usage pattern for the label ('baseline', 'after sort key'), so an agent knows the intended workflow. It does not name when NOT to use it (e.g., use workload_stop to end a run), so it stops short of a full when/when-not treatment.

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