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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: the explicit exclusion of officers, directors, registered agents, emails, phones and street addresses, the provenance rule for the website field ('its own pages show the exact legal name and the same city or state'), and the partial-failure contract ('if one state fails the others still return and the failure is listed in missing'). Its limitation is that it doesn't say how records are ordered or paged across states beyond 'newest first'.

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 paragraph is dense but front-loaded: what it searches, then what each mode is for, then exclusions and caveats. Nearly every sentence carries operational information. Minor cost is the run-on packing of mode descriptions and caveats into one block, which makes scanning harder than a short structure would.

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, five-source, no-output-schema tool, the description covers the things an agent cannot infer: data excluded from records, website field semantics, per-state publishing cadence and status coverage, and degraded-result behavior via 'missing'. Nothing needed to call it correctly or interpret partial results is missing.

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 100%, so the baseline is 3, but the description adds interpretive value the schema doesn't: state-level publication limits mean a missing NY/OR/PA entity 'may be inactive or unregistered', which changes how an agent should read status filters and empty search results. The rest (mode roles, entity_numbers not unique across states) largely duplicates the schema text.

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 first sentence names the concrete resource (official Secretary of State business registers of NY, CO, OR, CT, PA) and the three modes and their distinct jobs are spelled out: 'new' as a formation-date feed, 'search' by legal name, 'lookup' by state entity number. That is enough to distinguish it from siblings like company_lookup, search_company_registry and validate_vat without opening the schema.

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 names both use cases and the mode that serves each: 'use it for new-business leads ... and prospecting' for mode new, and 'use them for KYB ... on a supplier or counterparty' for search and lookup. It also gives coverage caveats that steer choice (NY/OR/PA publish active entities only; PA is monthly, so its records lag).

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