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

No annotations exist, so the description carries the full burden, and it discloses the exact output payload per operator (IGR with size-class median and position, IDSS, access-to-care band, 5-year fines count, small-group readjustment). It doesn't mention behavior on unknown/ambiguous operator names or error handling, which is the main remaining gap for a no-annotation 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 purpose is front-loaded in the first sentence and the example phrasings immediately follow. The 'For each operator' list is long but each item is load-bearing output detail, so it earns its space despite the density.

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 2-param read tool with no annotations, the description covers scope, inputs, and output contents thoroughly; the existence of an output schema means the enumerated metrics are bonus rather than required. Missing only edge-case behavior (invalid or ambiguous operator identifiers), which prevents a 5.

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 0%, so the description must compensate, and it does: it defines accepted operator identifier forms (names, CNPJs, ANS registry numbers) with an example, and enumerates the coverage values ('medica' default, 'odonto') that the schema leaves as a bare string. It could clarify what medica vs odonto changes in the output, keeping it from a 5.

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 (side-by-side comparison), resource (health-plan operators), and scope (2 to 8 operators on ANS indicators). This clearly distinguishes it from operator_profile (single operator) and rank_operators (ranking), so an agent can pick it 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?

The description gives concrete triggering questions ('Amil or Bradesco Saúde?', 'compare the plans my company offers'), which clearly signals the use case. It doesn't explicitly state when NOT to use it or name the sibling alternatives (rank_operators, operator_profile), so it falls 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.

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

With no annotations, the description carries the full burden and does well: it discloses result ordering ('Largest first'), the default and maximum result count (10, max 50), that modality is a substring match, that query words are ANDed, that accents/case are normalized, and a non-obvious domain caveat that head office is not where the operator sells plans. It does not state pagination behavior or explicitly frame the operation as read-only, so it is not exhaustive.

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?

Front-loaded with a one-sentence purpose, then usage, then an Args block, then the return shape — a clean, scannable structure. The modality enumeration is long but each value is a legitimate allowed input, and every section earns its place; only minor tightening is possible.

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 zero-required-parameter search tool with an output schema present, the description supplies everything an agent needs: what it searches, how matching works, ordering, limits, cancellation handling, and even a summary of returned fields. Nothing material is left to inference.

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 0%, so the description must compensate entirely, and it does: every one of the six parameters is explained with examples, defaults (limit default 10, max 50; include_cancelled semantics), and matching rules (substring for modality, all-words-must-match for query, accent/case insensitivity). This adds real meaning that the bare schema titles could never convey.

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 — find Brazilian health-plan operators registered with ANS — and immediately gives the two concrete jobs it performs (brand name → ANS registry number, or listing by geography/type). This is clearly a discovery/lookup tool, distinguishable from siblings like operator_profile, compare_operators and rank_operators which operate on already-identified operators.

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?

Explicitly names the triggering scenario ('turn a brand the user mentions ("Unimed BH", "Amil") into the ANS registry number') and the alternative scenario (list by state, city or type), which is exactly the when-to-use guidance an agent needs. It does not name sibling tools or state exclusions, 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.

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

With no annotations, the description carries the burden well: it discloses the full data scope (six domains), the meaning of directionality (IGR lower-is-better, IDSS higher-is-better), and an important silent fallback ('the largest active one is used') with a pointer to outras_operadoras_com_nome_parecido for verification. It omits any statement about permissions, rate limits, or read-only nature, which keeps it short of a 5.

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?

Front-loaded purpose, then a scannable bulleted return breakdown, then args — good ordering with no filler sentences. The per-field return enumeration is somewhat long given an output schema already exists, which is the main redundancy.

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 agent has everything needed to call it correctly: input formats, ambiguity handling, coverage default, and interpretation guidance for the returned metrics (with a pointer to como_ler). Since an output schema exists, the description is not obliged to enumerate return fields further.

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 0%, so the description must do all the work and it does: 'operator' accepts name/partial name, CNPJ, or ANS registry number, and it explains the multi-match resolution behavior. 'coverage' gets its two allowed values ('medica'/'odonto') and its default, which the schema's untyped anyOf string/null cannot convey.

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?

Opens with a specific verb-scoped statement: 'Everything ANS publishes about one health-plan operator', plus the decision it supports. It is clearly an entity-detail tool and is distinguishable from siblings like compare_operators or rank_operators, which act on multiple operators.

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?

Example questions ('is Hapvida good?', 'has SulAmérica been fined?') make the intended use case concrete and give the agent a trigger pattern. It does not explicitly state when to prefer find_operators or compare_operators instead, so the routing guidance is implied rather than spelled out.

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?

With no annotations, the description carries the burden well: it explains ranking direction, defaults, the ANS same-size comparison constraint, and why tiny operators are excluded by default. It does not explicitly declare read-only behavior or permissions, but the ranking/query nature is clear and the output schema covers return structure.

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 description is front-loaded with purpose and concrete examples, then efficiently documents each parameter. Despite eight parameters, every line adds useful information without repetition.

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?

The description is substantially complete for a complex eight-parameter tool: all parameters are explained, output schema covers return values, and key caveats are included. The main remaining gap is explicit routing guidance versus sibling tools such as compare_operators and find_operators.

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 must compensate for all eight parameters. It does so thoroughly: it defines allowed values for by and coverage, explains porte thresholds, clarifies that uf means head-office state, gives modality examples, and documents defaults and limits.

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: ranking active health-plan operators by complaints or quality. The example questions make the ranking purpose concrete, though it does not explicitly contrast itself with sibling tools such as compare_operators or find_operators.

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 provides clear usage contexts through example questions like 'which large health plans get the fewest complaints?' and 'best-rated dental plans'. It does not explicitly state when to choose this over sibling tools, but the intended use cases are clear.

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?

With no annotations present, the description carries disclosure duty, and it does add provenance the schema cannot express: each channel was 'checked on the ANS consumer-service page (conferido_em)'. It doesn't discuss return shape or how many channels come back, but for a zero-parameter read-only guidance lookup the behavioral risk surface is minimal.

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?

Three short lines: what it returns, when to call it, and how the data was verified. The trigger sentence is front-loaded right after the purpose statement and no sentence is filler.

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 description needn't spell out the return format, and it already covers purpose, trigger and data provenance. What is slightly missing is any hint of scope limits (e.g. whether it covers only ANS-regulated plans vs. employer self-funded plans), which matters for this domain.

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 there is nothing semantic to explain and the baseline for an argument-free tool applies. The description correctly implies a no-input lookup by not suggesting any audience/state/locale scoping.

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?

Names a specific resource and scope: 'the official ANS channels and the steps' for complaining about a Brazilian health plan. The sibling tools (operator_profile, find_operators, compare_operators, rank_operators) are all operator-data tools, so this guidance tool is unambiguously distinct from every one of them.

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?

Gives an explicit trigger: 'Use when a user's plan denied or delayed a procedure, or they have a contract problem.' That is a clear invocation condition covering the two main scenarios. It does not name an alternative or exclusion, but no sibling could plausibly be confused with it.

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