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

The description adds genuinely non-schema behavior: the first 10 rows are free and further rows cost credits per 100, which is critical context for an agent and is not implied by readOnlyHint=false (a hint the annotations leave ambiguous for a retrieval tool). It also discloses the visible field set, which matters because no output schema exists. It stops short of covering pagination behavior, what happens when credits are exhausted, or result ordering.

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, front-loaded with what is returned and followed by cost and filter constraints, with no filler. The parenthetical field inventory is long but earns its space given there is no output schema; only the missing pagination mention keeps this from being fully complete in minimal space.

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 nine-parameter, credentialed, paginated read tool with no output schema, the definition covers returns, cost, and most filters — the pieces an agent most needs to call it correctly. What remains thin is pagination (limit/offset interaction) and ordering, small relative to what is already disclosed.

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 only 22%, so the description must compensate, and it does for six of nine parameters — q as an address fragment, since in YYYY-MM-DD form, and especially stacked=true meaning 'addresses on more than one list' (a meaning the schema does not convey). The gap is limit/offset: neither is mentioned, so pagination semantics and the 1000 maximum remain undocumented in both places.

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 opens with a concrete verb+resource ('Rows of one compliance list') and enumerates the returned fields (address, ZIP, dates, status, agency id, source link, cross-list membership), which tells an agent exactly what it retrieves. It doesn't explicitly contrast with siblings such as list_compliance or get_compliance_changes, so the boundary between listing lists and listing rows is left to inference.

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?

Usage is implied through the filter inventory (zip, q, status, type, since, stacked) and through a cost cue pointing at get_store, so an agent can infer how to narrow a query. However there is no explicit when-to-use / when-not-to-use statement versus list_compliance, get_compliance_changes, or search_records, and no guidance on choosing limit/offset over filters.

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