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

Beyond the readOnly/idempotent annotations, the description discloses the 25-result-per-call cap, the meaning of total_capped (lower bound) and total_unknown, the per-source data_through/coverage_window/count_unit metadata, and that coverage varies by source and place. These are exactly the caveats an agent needs to avoid over-claiming completeness, and none of them are derivable from the annotations or schema.

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 most important content (what is searched, the record_kind default, the empty-result caveat) is front-loaded, and each subsequent sentence carries distinct semantic information. The total_capped/total_unknown pair and the _notes pointer are slightly terse and reference artifacts the agent must resolve elsewhere, which keeps it from a 5.

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 20-parameter, zero-required search with no output schema, the description covers the key ambiguities: result cap, total semantics, coverage limitations, and where pagination guidance lives. It does not explain the interaction between page/start or the radius_miles/coordinate pairing, but those gaps are modest relative to the schema's own detail.

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 90%, so the schema already documents nearly every parameter, including the detailed record_kind enum. The description's parameter-level contribution is largely a restatement of the filter dimensions listed in the schema, adding only the general 'complaints are never counted as violations' framing. Baseline 3 is appropriate when the schema does the heavy lifting.

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 opening sentence gives a specific verb (search) and resource (agency findings/violations) plus the filterable dimensions, and the record_kind sentence separates violations from complaints. It does not explicitly distinguish itself from the many sibling search_* tools, but the violation/complaint framing makes the resource scope clear enough to select it.

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 states the default (record_kind=violation) and warns that complaints are unconfirmed reports, which steers the agent's choice of record_kind. It also sets an interpretive rule (empty results do not establish absence) and points to _notes for pagination. It lacks explicit 'use X instead' routing to siblings, so it stops short of a 5.

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