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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description nonetheless adds real behavioral context beyond them — matching semantics ('name contains-search'), result ordering ('newest first'), data freshness tied to each state's portal, and, importantly, a billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). Disclosing that failures are free and which chains are accepted is exactly the kind of detail an agent needs before invoking a paid tool.

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 lead sentence is well-structured and front-loaded, but the remainder is bloated with an off-topic sibling cross-sell that devolves into a broken fragment ('not from AllTrails, which.'). The pricing sentence, while useful, is long-winded ('Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc)'). Roughly half the text does not earn its place.

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?

An output schema exists, so the enumerated return fields (entity ID, name, type, status, jurisdiction, formation date, addresses, registered agent) are redundant but harmless. Combined with the state coverage limits, refresh cadence, and cost model, an agent has enough to call this correctly and predict the charge. The only real gap is guidance on the per-state limit semantics.

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 100%, so all three parameters (name, limit, states) are already documented in the schema and the baseline is 3. The description adds only marginal semantics beyond that — 'contains-search' clarifies substring matching and 'newest first' clarifies ordering. It adds nothing about the per-state interpretation of 'limit' or about combining the states parameter with limit, which would have been the useful increment.

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 specific verb-and-resource statement: 'Business entity search in official Secretary of State open data' scoped to Colorado, New York, and Oregon, with coverage qualifiers per state (all entities / active corporations / active businesses). That is far more precise than the title alone. Sibling differentiation is only attempted via an appended cross-reference list that routes to unrelated tools (social_upwork, social_alltrails), which does not actually clarify how this differs from any nearby search tool.

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?

There is a genuine when-not constraint: 'Only these three states' and 'refresh follows each state's portal', so an agent knows the coverage limit. However, the stated alternatives are off-topic ('social_upwork when you need Upwork open jobs', 'social_alltrails when you need Hiking trails'), which is boilerplate cross-selling rather than guidance for choosing between comparable entity-search tools. Usage is therefore implied through scope, not explicitly directed.

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