ads_watch

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

Adds substantial context beyond the read-only annotations: notification-based (PLC-timestamped, task-cycle) vs fallback polling, the 'method' field indicating which path ran, hard caps of 60 s / 5000 rows, and the off-worker wait semantics. These are exactly the behavioral traits an agent needs and none are in the annotations.

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?

Purpose is front-loaded and every clause carries information, but the single dense paragraph with dashes, parentheses and a trailing three-use-case list is harder to scan than it needs to be. Efficient, if a bit overloaded.

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 values need not be described, and the description covers the behavioral gaps that remain (caps, notification vs polling, concurrency semantics, alternatives). Nothing an agent needs to invoke this correctly is missing.

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 coverage is 0%, so the description must carry the load, and it does: change_only's true/false semantics, interval_ms's 'one sample per interval', and duration_ms's 60 s cap are all explained. Only 'names' is left undefined, though its meaning is self-evident.

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+resource+scope: 'Trace symbols for duration_ms', which is distinct from point-read siblings like ads_read/ads_read_many and from ads_wait_until. Combined with the notification/polling explanation, an agent can tell exactly what class of operation this is.

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 concrete usage semantics (change_only=true records changes, false is one sample per interval_ms) and explicitly routes a specific case to alternatives: 'for stimulus→response use test_response, or rec_start + the write + rec_stop'. It does not, however, directly frame when to prefer this over plain ads_read/ads_wait_until for a simple timed capture.

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