watch_requests

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

With no annotations, the description carries the full burden, and it does disclose the most important trait: this is a non-streaming pull loop, not a subscription. It omits retention/expiry behavior for old cursors, ordering guarantees, and any rate-limit or cost note, which matter for a repeated-poll 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, payload first, calling mechanics second — well front-loaded with almost no waste. The only inefficiency is the ambiguous 'next_after' reference, which costs a moment of interpretation rather than adding clarity.

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?

The tool is simple and an output schema exists, so return values need not be explained. Still, for a cursor-based poller the description should resolve what the next cursor is and what happens when 'after' is stale or past retention, and it leaves that gap plus the next_after/after ambiguity unresolved.

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 coverage is 50%: 'after' is documented in the schema while 'limit' is not. The description adds cursor-advance semantics but refers to 'next_after', a name that does not exist in the input schema, leaving the agent to guess whether that is a response field or the same thing as 'after'.

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 states a concrete payload: raw lifecycle events (request_created through response_complete/failed) retrieved since a cursor. That is specific enough to separate it from list_requests or get_status, though it never names a sibling or explicitly contrasts 'raw events' with the summarized views the other tools return.

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?

It explains the calling pattern well — this is a pull, re-invoke to get newer events, it does not stream — which is genuine usage guidance for polling. However it gives no selection criteria against siblings (list_requests, search_traffic, get_session_summary), so an agent knows how to call it but not when to prefer it.

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