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

Annotations already declare openWorld=true, readOnly=false and destructive=false, so the safety profile is covered. The description adds genuinely new behavioral facts: the agent checks skills and workflows for reuse, idempotencyKey must be stable, credits and concurrent-run limits apply, and polling continues via agent_run_get. It doesn't explain what the initial response returns or what happens on duplicate keys.

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?

Six short sentences with the core action front-loaded and each sentence carrying a distinct instruction (routing, reuse check, idempotency, next step, limits). The telegraphic phrasing is efficient, though 'Credits and concurrent runs have limits' is vague enough to be of marginal use without numbers.

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 9-parameter, nested-object, open-world mutation with no output schema, the description covers the lifecycle (start, poll) well but leaves the tenant/agent selectors, effort and reuse knobs unexplained. It is adequate to invoke the tool and follow up, but not to invoke it correctly in multi-workspace or budget-constrained settings.

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% across 9 parameters, so the description carries the full burden, yet it only touches idempotencyKey (calling it 'stable') and waitMs. Parameters like agentId, spaceId, effort, reuse, maxCredits, title and input.content get no meaning from either source, leaving the agent to guess at multi-tenant scoping and credit caps.

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 workspace agent on a new task') and immediately scopes itself against the sibling workflow_execute. An agent can distinguish this from agent_run_get/list/cancel and from workflow_execute without opening any schema.

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 routing rule: use workflow_execute when the workflow is already known, otherwise start an agent. It also prescribes the follow-up call (agent_run_get with waitMs). It stops short of stating when-not conditions such as already having a live run, so it falls just short of a 5.

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