start_swarm

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

With no annotations, the description carries the full burden, and it does add real value by disclosing the asynchronous contract ("Returns a job ID immediately - the swarm runs in the background"). It says nothing about the effect of safety_mode, resource/cost implications, whether the job can be cancelled, or what permissions are needed for a launch that spawns autonomous agents.

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?

Three short sentences with zero waste. The asynchronous return contract is front-loaded right after the purpose, and the follow-up pointer comes last.

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?

The async behavior and monitoring path are covered, and no output schema means the return value (a job ID) needn't be elaborated. But for a tool that launches autonomous background agents with a safety_mode override and no annotations, the description omits what safety modes mean, termination options, and any cost or blast-radius signal.

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 100%, so every parameter including the safety_mode enum is already documented in the schema. The description adds no syntax, format, or behavioral detail about goal, context, safety_mode, or workspace_path, so the baseline of 3 applies.

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 description gives a specific verb and resource ("Start an autonomous agent swarm") plus the scope qualifier "complex goal." It does not, however, distinguish itself from the sibling spawn_agent or run_pipeline, so an agent must infer whether a single agent or a swarm is the right primitive.

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?

It names the follow-up tool (get_task_status) for monitoring, which is genuine usage context, but offers no guidance on when to prefer this over spawn_agent, run_pipeline, or invoke_session, and no preconditions or exclusions are stated.

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