list_watch_events

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two useful behavioral facts beyond that: only *published* events are returned, and results are filtered by *current permissions*, implying callers may see a subset of matching events. It does not mention pagination behavior despite the cursor parameter, nor the shape of returned events.

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 sentence with no filler, and the key qualifiers (published, watch targets, permissions) are front-loaded. It earns its brevity but is arguably so terse that it omits operative details rather than being genuinely efficient.

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 paginated list tool with no output schema and no schema descriptions, the agent is left without guidance on pagination, result shape, ordering, or what an 'event' contains. The definition should do more to compensate for the absent output schema and undocumented parameters.

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 carries the burden of explaining three parameters and does not do so. 'watch targets' loosely gestures at watchlist_id, but limit and cursor are never mentioned in the description, and the schema itself offers only constraints (max 100, cursor maxLength 1800, UUID pattern) with no semantic descriptions.

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 ('Read') and resource ('published events'), and narrows scope to events matching watch targets and the caller's permissions. It is clear what the tool returns, but it never differentiates itself from closely named siblings like list_changes or get_evidence, which an agent could easily confuse with 'events'.

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 guidance, no when-not-to-use, and no named alternative. The phrase 'matching the watch targets' implies it follows a watchlist/watch-target setup, but an agent must infer that prerequisite and infer that list_changes is the tool for non-watch-related change feeds.

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