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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real behavioral caveats: coverage status measures stored bill/text availability only, timestamps can advance on count recomputation without new data, and statewide semantic freshness is unverified even for GREEN. These warnings meaningfully shape interpretation of results.

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?

The core return behavior is front-loaded, which is good, but the text is dense and stacked with undefined jargon ('state-machine status', 'bounded retained official-source observation health'), and the three trailing caveat sentences are compressed to the edge of parseability.

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, the description must convey return content, and it does: status per state, full matrix on omission, public-registry/unlisted row counts, observation health, and evidence links. The main gap is failing to explain the possible status values (e.g. what GREEN/BLACK mean) beyond warning about freshness.

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% and the single 'state' param is undocumented in the schema, so the description carries the load. It specifies the acceptable forms (abbreviation or name) and the important semantic that omission yields the full stored coverage matrix, which is the key behavior of this argument.

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 names a specific verb and resource ('Return the jurisdiction_coverage state-machine status') and states the two modes of operation (single state vs full matrix when state is omitted). No sibling covers jurisdiction coverage, so it is naturally differentiated, though the 'state-machine status' framing is jargon-heavy rather than plainly self-explanatory.

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 implies when to use which mode — pass a state for one jurisdiction, omit it for the full matrix — but never states purpose-driven conditions or exclusions (e.g. when to prefer this over get_bill_record for coverage questions). Usage is inferable rather than explicit.

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