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

With no annotations, the description carries the full behavioral burden, and it discloses meaningful side effects: HTTP MCP injection with a short-lived token, one-agent-per-work-item concurrency, busy-run status semantics, and conditional playbook/skills prepending with a cap. It stops short of clarifying what the cap is or the token lifetime, and some jargon (tsk_, bc-) is unexplained, but these are minor against the substantial disclosure.

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 definition is front-loaded with the core purpose and every subsequent sentence carries information with no filler. The density hurts a little — 'TeamShared', 'tsk_', and 'bc-' are unexplained internal jargon — so it sacrifices some readability for completeness.

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 tool with 8 parameters, no annotations, and a complex behavioral profile (two launch modes, injection side effects, concurrency limits), the description covers the important operational facts, and an output schema is present so return values need no description. What's missing is a tie-back to sibling tools (e.g., what to use when status=busy) and clarification of 'capped', which leaves the agent to guess at the playbook limit.

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 baseline is 3. The description adds real semantics beyond the schema for work_id — playbook_slug triggers prepending of the named playbook and its cited skills, capped, with no injection when the slug is unset or work_id omitted — which instructs an agent on that parameter's behavioral effect. Other parameters are already well described in the schema, so no further compensation is needed.

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 sentence states a concrete action with a concrete resource: start a Cursor cloud agent. The worker-vs-dispatcher distinction scopes two mmsodes, and the verb 'start' cleanly separates this from sibling tools like agent_run_cancel, agent_run_followup, agent_run_list, and agent_run_status.

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 provides strong operational context — a busy run returns status=busy instead of a second id, so an agent learns not to expect a second run for a busy work item — but it never names an alternative tool or states when not to use this one. The worker/dispatcher and playbook-injection rules guide parameter choice, yet tool-vs-tool routing is left implicit.

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