start_zones

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

The description adds behavioral context beyond annotations: it states that zones run 'in sequence' and defines the zones format. Annotations indicate readOnlyHint=false (so mutation is expected) and destructiveHint=false (not destructive). The description aligns with these (starting a run is a mutation but not destructive). However, it does not disclose potential side effects (e.g., if a run is already active, or what happens to overlapping schedules). The behavioral transparency is adequate but not exhaustive.

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: a one-line summary followed by a detailed parameter breakdown. It is informative but slightly verbose (e.g., repeating 'zones' explanation twice). However, it front-loads the purpose and uses clear formatting (args list). It earns its length by adding value, but could tighten redundancy slightly.

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 the tool's complexity (5 parameters, manual run initiation) and the presence of an output schema (so return values are not required), the description is complete. It covers all parameters, explains the zones format concretely, references a sibling tool (list_zones) for required data, and describes the cycle-soak functionality. No gaps are apparent.

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 provides detailed semantics beyond the input schema, which only gives types and defaults. It explains that zones is a list of dicts with specific keys ('zone_number' and 'duration'), specifies that zone_number is a 1-based hardware slot (not UUID) found via list_zones, and describes the role of cycle_soak and its associated parameters. This adds critical meaning, especially since the schema defines zones as 'array of object' with no inner structure validation.

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 'Start a manual run of one or more zones in sequence,' specifying the verb (start), resource (zones), and context (manual, sequential). This distinguishes it from sibling tools like run_schedule (which starts scheduled runs) and stop_watering (which stops current runs). The explicit mention of 'manual run' differentiates it from schedule-based actions, and the details about zone numbering via list_zones further clarify the resource.

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 context on when to use the tool (e.g., for a manual run) and hints at prerequisites (finding zone_number via list_zones). However, it does not explicitly state when not to use it or mention alternatives (e.g., run_schedule for scheduled runs). The description lacks exclusion criteria or comparative guidance, leaving the agent to infer usage boundaries.

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