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

With no annotations, the description carries the full burden and does so well: it discloses the free-tier interval floor (interval_s >= 300), that Ned POSTs a signed test callback to callback_url within 60s, that firing happens only on change, and that the agent_key is returned once and must be stored. It stops short of describing failure modes or what happens on invalid targets.

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?

Dense and front-loaded — the operation and type enumeration come first, followed by parameter semantics and then the bootstrap flow. Telegram-style phrasing is compact without padding, though the run-on lines trade some readability for brevity.

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 5-param mutation tool with no annotations, 0% schema coverage, and no output schema, the description covers nearly everything an agent needs: types, target rules, condition shapes, interval floor, callback timing, and the agent_key bootstrap. Only callback_url expectations and error behavior are left implicit.

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 0%, so the description must compensate and largely does: it maps type values to target semantics (URL for http/tls, omit for deadman), gives per-type condition examples (warn_days, grace_s, max_ms), and states the interval_s constraint. callback_url is only implied by the callback behavior rather than explained directly.

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 ('Register a watch') and immediately enumerates the supported watch types (http | tls | deadman), so the agent knows what operation this is. It does not explicitly differentiate itself from siblings like watch_get or watch_cancel, but the name and type enumeration make the distinction obvious.

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?

Provides useful workflow context — the bootstrap sequence (call without an agent key first, store the returned agent_key, pass it as NED_AGENT_KEY next time) is clear guidance for a first-time caller. However, it never states when to prefer this tool over watch_get/watch_cancel or what prerequisites (e.g., auth) are otherwise required.

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