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

Goes well beyond the annotations by disclosing asynchronous execution (returns a task_id immediately, poll with get_task_status until succeeded or failed), the non-destructive outcome (draft saved for review, never deployed from here), and the two named terminal result states. Annotations only flag readOnly/destructive/idempotent/openWorld flags; the description supplies the actual workflow semantics an agent needs.

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-loads purpose, then async behavior, then the two result-state branches, so an agent can stop reading early. It is information-dense with no filler, though the later sentences are long and semicolon-heavy, which slightly slows scanning of the conditional branches.

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 exists, so return-value documentation is unnecessary, and the description correctly spends its budget on routing, async polling, and the non-deployment guarantee instead. The only gaps are the unmentioned 'name' and 'idempotency_key' parameters, which matter given the annotation declares idempotentHint=false.

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 four parameters, so the description carries the burden. It does add real value for target_platform by narrowing the three-value enum to 'claude only for now', and it frames task_description as the user-described task, but 'name' and 'idempotency_key' are never mentioned, so half the parameters remain semantically opaque.

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 ('Draft a new Dactic agent') plus a decisive scope constraint: built only from the user's own Dactic skills, policies and work context. It distinguishes itself from the two nearest siblings, create_agent_from_process and deploy_agent, by saying the result is a draft that is never deployed from here.

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 explicit routing rules rather than vague context: on a not_enough_material result, offer create_agent_from_process; on existing_agent_covers, use create_agent_from_process only for a genuinely new process. It also sets a procedural precondition ('Confirm the task with the user before calling') and scopes the platform ('claude only for now'), leaving little to inference.

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