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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it explains the return shape, that cancelled watches are excluded, that results are sorted newest first, that heartbeat fields are included, and that a blank key returns a signup link. It also clarifies billing ('Never billed'). This is strong added context, though it doesn't detail pagination or error cases beyond the blank-key case.

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 front-loaded with the most important usage signal ('WHEN you need to see what you are subscribed to'), then gives the return shape, then the key requirement, then the sibling distinction. Every sentence earns its place; the example payload is compact and informative. It is longer than a one-liner but each clause adds distinct value.

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 read-only list tool with no required parameters and no output schema, the description is quite complete: it covers purpose, return shape, sorting, exclusions, heartbeat semantics, auth, billing, and sibling differentiation. The only minor gaps are lack of explicit pagination behavior and no mention of error responses beyond the blank-key signup link, but these are not critical for a simple list 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?

Schema description coverage is 100% for the single parameter, and the schema already explains that plane_api_key is deprecated and should be passed via header or omitted for demo mode. The description reinforces this by saying 'Needs your key: a blank one returns a signup link,' which adds a behavioral consequence of omitting the key. Since the schema covers the parameter well, the description's marginal addition is modest but useful.

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 opens with a clear WHEN and a specific verb+resource: 'see what you are subscribed to' and explicitly contrasts with cancel_watch by noting it returns the id that cancel_watch takes. It also distinguishes itself from watch_subscriptions (plane-owned) and states it lists live watches newest first, excluding cancelled ones. This is a specific, well-scoped purpose that an agent can act on without opening the schema.

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 gives explicit usage context: use it before adding a watch or to find the id for cancel_watch. It also names the alternative watch_subscriptions and states it is plane-session only, which tells the agent when not to use this tool. The note about needing a key and demo mode further clarifies invocation conditions.

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