prufa_start_monitor

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

With no annotations, the description carries the full burden. It discloses idempotency via idempotency_key, that deploy_hook is returned once and must be stored immediately, and that free-tier gets a 402 with a pass-through hint. It does not detail failure modes or monitor creation timing.

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 description is well-structured with front-loaded purpose in 4 sentences. Slightly verbose but no unnecessary words; could be tightened slightly while maintaining clarity.

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?

Given no output schema, the description explains the deploy_hook return and storage requirement, plus idempotent behavior. Missing details like monitor ID or status, but sufficient for a start operation.

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?

The description adds meaning beyond schema for all 4 parameters: url, cadence (enum repeated), flow_id (contrast with plain audit), and idempotency_key (makes retries safe). Compensates for 50% schema coverage with clear context.

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 clearly states the tool starts a persistent monitor that re-runs QA audits on a cadence and fires a deploy hook on regression deltas. It uses specific verbs ('Start') and resources ('monitor'), and distinguishes from one-off tools like prufa_run_audit.

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 explicit context on when to use flow_id vs plain audit and mentions free-tier behavior (402 error with checkout hint). However, it does not explicitly contrast with sibling tools like prufa_run_audit or prufa_trigger_monitor.

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