agent_prompt

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

With no annotations, the description carries the full behavioral burden and does meaningfully disclose side-effect semantics: preflight/pre-spawn rejection produces no submission, while timeout/cancellation after 'Herdr starts' may leave the task submitted and is unsafe to auto-retry. That non-idempotency warning is high-value for a mutation tool, though auth requirements, blocking/wait behavior, and agent state changes are unaddressed.

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?

Two tight, front-loaded sentences with no filler: purpose first, then the failure/retry semantics. The unexplained term 'Herdr' is the only blemish; otherwise it is efficient.

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 6-parameter tool with no annotations and no output schema, the description covers the risk profile well but omits the operational core — what wait/until/timeoutMs actually do to the call — and returns nothing about outcomes. Adequate on safety, thin on mechanics.

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 only 17% (agentId alone is documented), so the description must compensate for task, wait, until, skills, and timeoutMs. It adds nothing about these parameters — notably the until enum values (idle/working/blocked/done/unknown) and the wait/timeout interaction are left entirely to the agent's inference.

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 ('Submit a task to an MCP-managed coding agent'), which an agent can distinguish from agent_send_keys, agent_start, and process_write without opening a schema. It does not explicitly name a sibling for contrast, so it falls short of a 5.

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?

'After a positive readiness check' implies a precondition (presumably agent_start/agent_get first), and the retry caveat tells the agent when not to re-invoke. However, no alternative tool is named and the readiness-check prerequisite is never spelled out, leaving usage largely inferred.

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