Check Watches (alerts)

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

With no annotations, the description carries the full burden and does so well: it discloses that output is delta-only ('returns only what's new'), that calling it has a stateful side effect ('rolls baselines forward'), that routine forms such as Form 4/13F are suppressed by default, and that the SEC index may lag ~1h due to caching. These are the exact traits an agent needs to avoid double-counting alerts or misreading missing filings.

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?

Four tight sentences, front-loaded with what it does and what it returns, followed by the suppression rule, the scheduling guidance, and the latency caveat. Nothing is redundant with the name or title.

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 output schema and no annotations, the description still conveys return semantics (delta-only), state mutation, filtering behavior, and a latency caveat — everything an agent needs to schedule and interpret 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. The description correctly implies scope ('every watch') without implying hidden selector arguments.

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 precise verb ('Check') and resource ('every watch'), then names exactly what counts as a change: new SEC filings and changed page content. An agent can tell instantly this is the polling/alert-feed counterpart to the sibling watch_manage tool.

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?

Explicitly prescribes the usage pattern: 'Run it on a schedule (cron / scheduled agent) to turn veris into an alert feed,' which tells the agent this is not an ad-hoc call. It does not, however, name watch_manage as the alternative for creating/editing watches, leaving that routing to inference.

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