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

Annotations already establish that this is read-only, idempotent, and non-destructive. The description adds concrete behavioral detail by naming what the call exposes (interval, last beat, overdue, fired, exhausted), which goes beyond the annotation information and helps the agent understand the response.

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?

One dense, front-loaded sentence states the operation and the key state fields with no filler. Every word contributes to the agent's understanding.

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 low-complexity read-only status lookup with fully documented parameters and safety annotations, the description is nearly complete. The only minor gap is the lack of error semantics for an unknown watchdog name, but the listed state fields give a solid picture of what to expect.

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%, and the schema already explains the deprecated vigil_key and its preferred replacement. The description adds no parameter-level guidance, so the schema carries the semantic burden; baseline 3 is appropriate.

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 uses a specific verb ('Read') and identifies the resource ('a watchdog's state') while enumerating the exact state fields returned (interval, last beat, overdue, fired, exhausted). This is clearly distinct from siblings like vigil_set_watchdog or vigil_heartbeat.

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 intended use is implied by 'Read a watchdog's state' and the readOnlyHint. However, the description does not explicitly state when not to use it or point to alternatives, so an agent must infer the right choice from the verb and sibling names.

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