dv_watch_events

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: that consumption uses an independent per-caller cursor and that reading leaves events in place, which matters for a watch/queue tool.

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?

Two short sentences with zero filler; the core action is front-loaded and the non-destructive caveat follows immediately.

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?

An output schema exists, so return values need not be explained. However, with zero parameter documentation, no guidance on cursor advancement relative to after_seq, and no routing to sibling tools, the definition is only minimally sufficient for calling this tool correctly.

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% for three parameters (limit, watch_id, after_seq), so the description carries the full burden. 'Delivery cursor' loosely gestures at after_seq, but limit, watch_id, and the 1-100 bound/defaults are entirely undocumented, leaving the agent to infer them from the schema alone.

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 and resource ('Read durable events') plus the mechanism ('independent delivery cursor'), which is enough to separate it from the write-oriented watch siblings (dv_watch_create, dv_watch_ack, dv_watch_delete). It does not name a sibling explicitly, so it falls short of full differentiation.

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?

Usage is only implied: the note that reading 'does not acknowledge or remove events' hints that dv_watch_ack is the tool for acknowledgement, but the description never states when to choose this tool over dv_watch_check, dv_watch_list, or dv_watch_ack.

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