list_watches

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the useful fact that results include source counts and pending batch information, but says nothing about ordering, pagination, or whether pending batches reflect unacknowledged changes (the ack_watch_changes sibling suggests they might).

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 short sentence with no padding, and the core payload (names, source counts, pending batches) is front-loaded. The trailing 'after a new session' qualifier is the only weak element — it adds words without adding determinable meaning.

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 and no output schema, the description carries the burden of explaining what comes back, and it only gestures at that. Terms like 'source counts' and 'pending batches' are left undefined, and the relationship to the closely related get_watch_changes / ack_watch_changes pair is never clarified, leaving an agent to infer the workflow.

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 nothing for the description to disambiguate and the baseline of 4 applies. No misleading parameter claims are made.

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 (saved subscriptions/watches) and sketches the returned fields (names, source counts, pending batches), but the verb 'Find' is weaker than 'list all' and the phrase 'after a new session' muddies the scope rather than pinning it down. It does nothing to distinguish it from get_watch_changes or get_status among the siblings, so an agent must guess whether this enumerates watches or returns their contents.

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 explicit when-to-use or when-not-to-use guidance, and no named alternative. The trailing clause 'after a new session' hints at a trigger condition but is too ambiguous to function as routing — an agent cannot tell from this whether it should call list_watches or get_watch_changes first.

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