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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: newest-first ordering, cancelled-watch exclusion, heartbeat fields (last_fired_at, fires_last_7d, rate_limited, status) and the 'never billed' cost note. It also flags the auth requirement ('Needs your key: a blank one returns a signup link').

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?

Front-loaded with the WHEN clause and dense but purposeful. The inline JSON shape earns its place given no output schema exists. Slightly long, but every sentence carries information an agent needs.

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?

No output schema, so the description responsibly supplies the return shape (watches array with id, company_id, event_types, webhook_endpoint_id, status) and heartbeat semantics. Combined with the auth note, an agent has everything needed to call and interpret it.

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?

Single parameter at 100% schema coverage, where the schema already documents the deprecated plane_api_key. The description adds auth context beyond the schema ('Needs your key', blank key returns signup link), which is meaningful for invocation even though it is not a per-parameter spec.

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 ('List active watches') and immediately distinguishes scope: live watches, newest first, cancelled excluded. Distinguishes from `cancel_watch` and `watch_company` by clarifying what it returns and how its ids feed into the sibling.

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?

Explicit WHEN clause: 'before adding a watch, or to find the `id` `cancel_watch` takes.' Names the alternative sibling and the condition that selects this tool, leaving nothing to inference.

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