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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely new context: the call is free (cost signal that shapes call ordering) and results are grouped per state. It does not discuss rate limits or what a zero-match response looks like, but the output schema covers return shape.

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 purpose and the cost-based routing rule are front-loaded in a single sentence, then the args list follows. The arg block is long but every line carries format or default information absent from the schema, so there is little waste; the one sloppy phrase ("Comma-separated of LLC...") is minor.

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 an 11-parameter tool with zero schema descriptions, the definition covers every parameter, the default for formed_within, and the cross-parameter dependency. With an output schema present it need not explain return values, though it could say whether states-less calls are legal (all params optional) or what happens when no filters are given.

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 0%, so the description carries the full burden and does so for all 11 parameters: formats (two-letter states, 5-digit or 3-digit ZIP prefixes, 2-6 digit NAICS), worked examples, entity_type vocabulary, and the boolean filters. It also states non-obvious interaction rules the schema cannot express — formed_from/formed_to override formed_within, and states is required when city, county or zip is supplied.

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?

States a specific verb and resource plus the aggregation scope: "Count businesses matching the filters, per state." It also names the sibling it precedes (search_businesses), so an agent can distinguish it from both siblings without opening either 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?

Explicit routing rule with a rationale: "Free: use it before search_businesses," which tells the agent to cheaply size a result set before running the costlier search. It names the alternative but gives no explicit when-not condition or guidance on choosing between list_states and this tool.

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

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

Annotations already establish readOnlyHint, idempotentHint, and openWorldHint, so safety and repeatability are covered. The description adds value beyond them by disclosing that the call is "Free" (no credit consumption) and by defining the semantic windows behind each count category. It does not discuss freshness of the counts or caching, which would have been a further bonus.

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?

A single sentence front-loads the purpose and then defines the three count categories without filler. The nested parenthetical quoting is dense and slightly harder to scan than a short bulleted breakdown would be, but nothing is redundant.

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?

This is a parameterless, read-only listing tool with an output schema that documents the return shape. The description supplies the one thing the schema and annotations cannot: what each count window means and that the call is free. Nothing needed to call it correctly 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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter meaning to add. The description does usefully map the labels "recent", "year", and "all" to concrete time windows, which likely correspond to fields in the output rather than inputs.

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 ("List the states ListRiver covers") and immediately clarifies the payload: business counts per state. The three metric windows ("recent", "year", "all") are spelled out precisely. It stops short of naming siblings like count_businesses or search_businesses, so the differentiation is implicit rather than explicit.

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: this is the coverage/overview call for enumerating supported states and their business volumes. There is no explicit when-to-use versus when-not-to-use statement and no pointer to the sibling tools for filtered or aggregate queries. "Free" gives a useful cost signal but is not routing guidance.

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

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

The annotations already cover read-only, open-world, and idempotent behavior, but the description adds an important non-annotated trait: each returned business has a cost every time it is returned. It does not detail authentication, rate limits, or result ordering, though the output schema likely covers return shape.

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 definition is front-loaded with purpose and cost warning, then uses a clean Args list. Every line adds useful information, and no parameter documentation is wasted.

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 13-parameter search tool with an output schema and annotations, the description covers purpose, cost behavior, pagination, all filter semantics, defaults, and conditional requirements. Nothing critical for correct invocation 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 description coverage is 0%, so the description carries the full parameter burden, and it succeeds. It documents all 13 parameters with formats, comma-separation rules, NAICS digit lengths, allowed entity-type values, date formats, limit range, cursor meaning, and a conditional requirement for states with city/county/zip.

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 states a specific verb and resource: "Get businesses matching the filters." It also links to count_businesses via "same filters as count_businesses" and makes clear this tool returns actual businesses, distinguishing it from the counting sibling.

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?

The description gives clear usage context by warning that each returned business counts and advising the agent to ask only for what the user needs. It also explains the cursor for paging. It stops short of explicitly saying when to use count_businesses versus this tool, leaving that inference to the sibling relationship.

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