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

With no annotations to lean on, the description carries the behavioral burden well: it discloses the registration-date cutoff baseline, that only firms registered after the cutoff are reported, and that poll_watchlist advances the cutoff so each firm surfaces exactly once. It still omits auth/permission needs and how often the watch is evaluated.

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 sentences with no filler, front-loaded on what is watched before explaining the cutoff mechanism. The second sentence is dense but every clause carries information about the polling contract.

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 2-parameter tool with no output schema and no annotations, the description explains the watch/cutoff contract but omits what an invocation actually returns or registers and how results are surfaced. It is adequate to start but leaves the operational picture (state, frequency, retrieval) partly inferred.

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 0%, so the description must compensate, and it does give shape to both parameters: 'code' is a CAEN activity code and 'county' is an optional scope. It adds no format guidance for the code (e.g., CAEN notation) and mentions a registration-date cutoff that is not actually a parameter, which could mislead about what can be passed in.

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 ('Watch a CAEN activity code ... for newly registered firms') plus an optional scope ('optionally scoped to one county'), so the agent immediately knows it is a registration-monitoring tool keyed on an activity code rather than a lookup. It does not explicitly contrast itself with the similarly named watch_company sibling, leaving that differentiation implicit.

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 references poll_watchlist in explaining that the cutoff slides forward, which implicitly tells the agent that poll_watchlist is the retrieval counterpart. However, it never states when this tool should be chosen over watch_company or the lookup_* siblings, nor what prerequisites exist before registering a watch.

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