list_watches

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description's remaining content (the state fields) describes return values, which an output schema already exists to convey, so it adds little behavioral context beyond what structured fields provide.

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?

A single, tightly-scoped sentence with the resource front-loaded and no filler. It is arguably too terse, but every word carries meaning and nothing is wasted.

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?

With no parameters, an output schema present, and read-only annotations, the definition is minimally viable: an agent knows it lists watches and their state. It still lacks any routing guidance among the many watch-related siblings, which is the main remaining gap.

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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline of 4 applies. Nothing in the description misrepresents or conflicts with the empty schema.

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 names the resource ("Surveillances") and enumerates the state fields returned (last check, slot count, last alert, error), which pairs with the list_* name to make the operation clear. It does not, however, distinguish itself from watch-related siblings like run_watches_now, watch_practitioner, or stop_watch.

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?

There is no when-to-use guidance at all — nothing says this is the read-side companion to run_watches_now/watch_practitioner, nor any prerequisite or exclusion. The agent must infer usage purely from the tool name and the sibling list.

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