voa-tiss

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

No annotations are provided, so the description carries the full disclosure burden, yet it says nothing about search semantics (substring vs fuzzy, ranking, whether results are snippets or full documents) or that the operation is a read-only lookup. For a search tool with zero annotation coverage this leaves meaningful behavioral gaps.

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 sentences, front-loaded with the core action followed by the use/avoid rules. Every sentence carries information; the only weakness is that brevity leaves the parameter and behavioral gaps unfilled.

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 return-value shape needn't be described, and the use/avoid guidance covers the routing decision. However, with 0% schema coverage and no annotations, the description is not complete enough about the 'limite' parameter and search behavior for an agent to call it confidently.

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% and the description never mentions either parameter. The meaning of 'texto' as a query string is inferable from context, but 'limite' (default 3, max 10) is undocumented anywhere, so the description fails to compensate for the coverage gap.

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-resource pair ('Busca trechos da documentação local da biblioteca'), which is clearly a docs-search operation distinct from the TISS/TUSS/operadora siblings. It doesn't name any sibling directly, so the differentiation comes from the exclusion phrasing rather than explicit routing.

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 explicitly splits 'Quando usar' (finding instructions and API references) from 'Quando não usar' (clinical data or specific codes), which is clear positive and negative guidance. It stops short of naming which sibling tool to use instead of the excluded cases.

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?

No annotations are provided, so the description carries the full behavioral burden. 'Explica' plus the interpretation framing implies a read-only lookup, and the low-risk shape is inferable, but nothing states side effects, permissions, or lookup scope beyond the table reference.

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 terse clauses, front-loaded with the purpose and then the use/avoid conditions. Every sentence carries signal, though the telegraphic 'Quando usar/Quando não usar' style is slightly clipped.

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 return values need not be described. For a single required parameter read tool, the description covers purpose and routing adequately; only the absence of any behavioral note (given no annotations) leaves a minor gap.

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%, and the schema only declares a 4-digit string pattern. The description compensates partially by identifying the code as a Table 38 ANS code, giving domain meaning the schema lacks, but it adds no format, examples, or error-handling detail.

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: explains a code from ANS Table 38. The usage line ('ao interpretar uma glosa recebida') further scopes it away from batch validation tools like tiss_validate, though no sibling is named explicitly.

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 gives both when to use ('ao interpretar uma glosa recebida') and when not to use ('para validar ou corrigir o lote'). That negation implicitly routes the agent to tiss_validate/tiss_apply_fixes, but those alternatives are not named, leaving some inference.

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?

No annotations exist, so the description carries the full burden; it does disclose the meaningful behavioral constraint that only ACTIVE operadoras are searched, which the schema does not. It says nothing about result ordering, pagination behavior, or what happens when no match is found, leaving the read semantics partly implicit.

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 compact sentences with zero filler: what it searches, when to use it, when to use a sibling instead. The core verb and resource are front-loaded, and the warning against misuse comes before any caveat.

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 return values need not be described, and the description adequately covers search semantics and sibling routing for a two-parameter read tool. The only shortfall is the undocumented 'limite' result-cap parameter, which affects how many hits an agent should expect.

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: it usefully explains that 'texto' is a multi-field query key accepting name, registro, CNPJ or locality. It never mentions the 'limite' parameter, its default of 10 or its maximum of 50, so half the parameters remain undocumented in prose.

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 ('Busca operadoras ativas') plus the searchable fields (nome, registro, CNPJ, localidade), so the agent knows exactly what the tool returns. It names tiss_rede as the wrong tool for hospital links, but does not distinguish itself from the closely named siblings operadora_perfil and operadora_rede.

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 'Quando usar' (locate an operadora in the public base) and 'Quando não usar' (hospital links → use tiss_rede) sections give real routing guidance rather than implied usage. The gap is that operadora_perfil and operadora_rede, which sound almost identical, are never mentioned.

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 provided, the description carries the full burden and does disclose that the response covers both the registration record and a semi-annual series of glosa and payment data. It implies a read-only consultation ('Consulta'), but does not state permissions, data freshness, or whether the semestral series can be empty.

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 sentences: what it returns, when to use, when not to use, with no filler. The scope statement is front-loaded before the routing guidance.

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 one-parameter read tool with an output schema already defining return shape, the description covers purpose, data retrieved, and the routing decision, which is nearly everything an agent needs. The only gap is that the alternative tool for name search is described but not named.

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 single parameter has 0% schema description coverage, so the description is the only place explaining it — 'pelo registro ANS' identifies registro_ans as the ANS registration number. However, it adds no format detail (the 5-6 digit pattern lives only in the schema) and does not say whether leading zeros matter or what happens with an unregistered number.

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 ('Consulta') and resource ('cadastro e a série semestral de glosa e pagamento de uma operadora na ANS'), defining scope beyond a mere lookup. The 'quando não usar' clause explicitly separates it from name-based operator search, which is what siblings like operadora_lookup do.

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 gives an explicit when-to-use ('para conhecer uma operadora pelo registro ANS') and when-not-to-use ('para buscar operadoras por nome'), a clear positive/negative routing rule. It stops short of naming the actual sibling tool (e.g. operadora_lookup), so the agent must infer which tool handles name searches.

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?

No annotations are provided, so the description carries the full behavioral burden. 'Consulta' implies a read operation, but the description does not explicitly state read-only behavior, permission requirements, rate limits, or other operational traits.

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 short, front-loaded, and structured around purpose, when to use, and when not to use. Every sentence adds routing value 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 output schema exists, so return values need not be explained. However, with no annotations and 0% schema description coverage, the description is still incomplete regarding parameter meaning and operational behavior.

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 should compensate but largely does not. It hints at UF-based filtering, yet the required 'registro' parameter and the 'limite' parameter are not explained at all.

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: querying establishments linked to an operator. It also explicitly distinguishes this tool from operadora_lookup, so an agent can tell which tool to select.

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 explicit 'when to use' guidance for identifying network units by UF and explicit 'when not to use' guidance pointing to operadora_lookup for the general registry. This is exactly the routing information an agent needs.

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?

No annotations are provided, so the description carries the full behavioral burden. It implies mutation by saying corrections are applied to the batch and warns against inventing missing data, but it does not disclose side effects, reversibility, atomicity, permissions, or how the batch is modified.

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 two sentences, front-loads the action, and immediately follows with when-to-use and when-not-to-use guidance. There is no wasted text.

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 tool is a mutation operation with nested opaque inputs and no annotations, and the description leaves key invocation details unspecified. The output schema covers return values, but the description still lacks enough parameter and behavioral context for safe correct invocation.

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%, and the schema uses opaque nested objects. The description names 'relatório' and 'lote' but does not explain the expected structure of report.findings or how JSON Patch corrections are encoded, so it does not compensate for the schema gap.

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: applying JSON Patch corrections from a report to the batch. It is clear what the tool does, though it differentiates itself from siblings mainly through usage context rather than an explicit contrast in the purpose statement.

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 explicitly says when to use the tool, after tiss_validate or tiss_audit with correctable findings, and when not to use it, for inventing missing data. The alternatives and boundary condition are named directly.

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 behavioral burden. The "to apply corrections use tiss_apply_fixes" clause implies this tool does not mutate, which is a useful signal, but it never states that explicitly and says nothing about which local rules run, determinism, or side effects.

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?

Four short sentences with the purpose front-loaded and the use/no-use guidance structured and clearly separated. Every sentence carries distinct information with no 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 return values needn't be described, and the routing guidance is present. However, for a complex tool with nested objects, 0% schema coverage and no annotations, the description leaves what inputs are needed and what the audit checks largely unexplained.

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% across 4 parameters including nested contexto and operadora objects. The description only mentions lote and "contexto da operadora" generically; it does not explain data, operadora format, or the nested contexto fields, so the parameter gap is largely unaddressed.

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 ("Audita") and resource ("lote JSON"), plus scope (regras locais e contexto da operadora). It explicitly distinguishes from tiss_apply_fixes, but not from the close sibling tiss_validate, so its role among the validation-family tools remains partly ambiguous.

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?

Contains explicit "Quando usar" (identify administrative inconsistencies) and "Quando não usar" (to apply corrections) clauses, and names the alternative tool (tiss_apply_fixes). The routing decision is fully stated, not inferred.

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?

No annotations are provided, so the description carries full behavioral burden. It says the tool generates XML, but discloses nothing about validation behavior, required permissions, side effects, error handling, or how request vs. response mode is selected.

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 front-loaded sentence with zero wasted words. It is perhaps overly terse, but the dimension itself rewards efficient structure and there is no repetition or fluff.

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 return values need not be explained. However, the input is an opaque nested object with no documentation, and the description does not explain how to select solicitação vs. resposta or what the required 'mensagem' must contain, leaving an agent unable to invoke the tool correctly without trial and error.

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 single required parameter 'mensagem' is a nested object with 0% schema description coverage and additionalProperties true. The description adds no information about what the payload must contain or how to structure it.

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 ('Gera'), artifact ('XML TISS 4.03.00') and domain ('autorização SP/SADT'), which clearly distinguishes it from parse/check siblings like tiss_autorizacao_parse and tiss_autorizacao_check. However, it does not explicitly differentiate from the generic tiss_build 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 no explicit when-to-use guidance, alternatives, or prerequisites. An agent can infer it is the build step for authorization XML, but nothing says when to choose it over tiss_build, tiss_autorizacao_check, or tiss_autorizacao_parse.

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?

No annotations are provided, so the description carries the full disclosure burden, yet it never says whether this is a pure read-only validation or performs a submission, whether it needs credentials/operator config, or whether it is deterministic. "Decisão explicável" hints at a reasoned verdict, which is the only behavioral signal offered.

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 front-loaded sentence with no filler; the verdict/explainability point comes last. It is efficient but so short that the missing guidance never gets said, so it is close to under-specification rather than tight writing.

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 return value needn't be explained, but for a 3-parameter tool with nested objects and no annotations the description should at minimum explain the xml/solicitacao/contexto split and how it differs from tiss_validate. Neither is present.

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% across three parameters, two of which are free-form nested objects with additionalProperties: true and zero property documentation. The description only loosely implies that "solicitação" is the SP/SADT payload and says nothing at all about "xml" vs "solicitacao" or what "contexto" should contain.

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?

"Valida uma solicitação SP/SADT" names a specific verb (validar) and resource (solicitação SP/SADT), and adds the outcome shape ("decisão explicável"). That is clear on its own, but it draws no line against tiss_validate, tiss_audit, or tiss_sandbox_autorizacao, all of which plausibly validate the same artifact.

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 no statement of when this tool should be chosen over tiss_validate, tiss_audit, tiss_autorizacao_parse, or tiss_sandbox_autorizacao, and no prerequisite (validated XML? a prior parse? real vs sandbox operator) is mentioned. The agent must infer routing from the name alone.

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, yet it says nothing about whether invalid or out-of-scope XML raises an error, what the parser tolerates, or whether it is strictly a read operation. Only the word "Interpreta" hints at non-mutation.

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 short sentence with no waste, but it is terse to the point of under-specification rather than efficient; nothing is front-loaded beyond the basic purpose.

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 output schema covers return values, so that need not be described, but given a parse tool over a complex EDI standard split across several sibling tools, the definition gives no guidance on accepted input variants, failure modes, or relationship to the check/build tools. It is not sufficient for confident invocation.

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?

There is one parameter ("xml") at 0% schema description coverage, and the description never mentions it — not its expected shape (raw XML string vs. base64 vs. file path), nor which document types are accepted. For a single undocumented param the description was the only place to compensate, and it does not.

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 ("Interpreta") and a specific resource ("solicitações e respostas de autorização SP/SADT"), and the 'parse' framing distinguishes it from siblings like tiss_autorizacao_build and tiss_autorizacao_check. It does not explicitly separate itself from tiss_parse_demonstrativo, which also parses TISS XML.

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?

No indication of when to reach for this tool versus tiss_autorizacao_check, tiss_autorizacao_build, or tiss_parse_demonstrativo, and no preconditions (e.g. whether the XML must be a raw SP/SADT guia or a full lote). Usage must be inferred entirely from the name.

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?

No annotations are provided, so the description carries the full disclosure burden; it names the hash computation as a side effect and implies the output is a serialized XML artifact. It does not describe whether the build is deterministic, what happens with malformed input, or error behavior, which would round this out for a tool with zero annotation coverage.

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 compact clauses: what it produces, where to find the schema, and the use/exclusion rules. Front-loaded with the core action; zero wasted sentences, and the exclusion rule comes last where it belongs.

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 return values needn't be explained, and the structural definition of the input is delegated to a named resource. For a single-parameter transformation tool, the description plus schema plus resource pointer covers everything an agent needs to invoke it correctly.

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% and the single 'lote' parameter is a free-form object whose schema explicitly points to tiss://schemas/lote. The description repeats that same pointer ('Consulte tiss://schemas/lote') rather than adding new meaning, so the baseline 3 applies — the schema and the delegated resource do the semantic work.

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: 'Gera o XML TISS 4.03.00 de um lote em JSON, com hash do epílogo' — naming the exact version and the output characteristic (epilogue hash). This is clearly distinguishable from siblings like tiss_validate (checks) and tiss_apply_fixes (corrects).

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?

Provides explicit when-to-use ('depois de validar o lote em JSON sem erros') and when-not-to-use ('para corrigir achados; use tiss_apply_fixes'), naming the alternative tool and the condition that routes to it. This establishes a precise pipeline position between validation and fix application.

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; 'Consulta' implies a read-only lookup, which is consistent, but it does not disclose behavioral traits such as default exclusion of expired domain entries (implied only by the schema's include_expired flag), result pagination via limite, or any permission/auth requirements. It adds a small amount of behavioral framing but leaves meaningful traits undisclosed.

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 clauses, front-loaded with the purpose, then usage and exclusion. Zero wasted words.

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 return values need not be described, but for a six-parameter, zero-coverage lookup tool the description omits how to actually drive the query (which of codigo/texto/tabela to supply, defaults, limits, expired-code behavior). It is complete on routing but incomplete on invocation.

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% across six parameters, so the description must compensate and does not: it never explains tabela, codigo, texto, limite, data, or include_expired, nor the dependentRequired rule that codigo needs tabela. Only the abstract idea of 'localizar um código ou termo' hints at the codigo/texto search modes.

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 (consulta) and resource (tabelas e códigos de domínio TISS), and explicitly distinguishes itself from the nearest sibling tuss_search. An agent can tell what this returns 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?

Gives an explicit 'quando usar' clause and an explicit 'quando não usar' clause that names the alternative tool (tuss_search) and the condition selecting it. Nothing is left to inference.

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?

No annotations provided, so the description must carry the full burden. 'Calcula' implies a non-destructive read-only computation and 'conferir a integridade' adds intent, but it doesn't explicitly state that it has no side effects or describe auth requirements. Adequate but not fully disclosed.

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 compact sentences, front-loaded with the purpose and then clearly routing to when/when-not usage. Every clause earns 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?

With an output schema present, return values needn't be described, and the purpose plus named alternative cover the essentials. Only the exact meaning of the 'epílogo' hash and the input format are left implicit.

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% and the single 'xml' parameter is undocumented in the schema. The description only implies the input is a TISS XML, which is largely inferable from the tool name and purpose. Adds little beyond the obvious.

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+resource: 'Calcula o hash do epílogo de um XML TISS'. This distinguishes it clearly from tiss_validate by scoping it to hash computation rather than content validation.

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 provides 'Quando usar' (check XML integrity) and 'Quando não usar' (to validate content) and names the correct alternative tiss_validate. This is textbook when/when-not/alternative 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?

No annotations are provided, so the description carries the full behavioral burden, yet it says nothing about whether this is a pure read/parse operation, what XML format or root element is expected, or how malformed input is reported. It only implies read-only behavior via the verb 'Lê'.

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, front-loaded clauses with no filler; the purpose leads and the usage guidance follows. Slightly telegraphic style, but nothing wasteful.

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 output schema covers return values and there is only one input, so the bar is modest, but with no annotations and an undescribed required XML input the definition leaves gaps an agent would hit on first invocation.

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 single 'xml' parameter has 0% schema description coverage, and the description adds no semantics for it — it is unclear whether it accepts a raw XML document, a base64 blob, or a file path. With one undocumented param the description needed to compensate and did not.

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 ('Lê decisões de um demonstrativo') and the when-to-use line adds the functional target (pagamentos e glosas). It distinguishes itself from validation siblings, though 'demonstrativo' remains a domain term the agent must already know.

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 gives a when-to-use ('identificar pagamentos e glosas') and a when-not-to-use ('validar lotes'), which is above the norm. It does not name the concrete alternative tool (e.g., tiss_validate), so routing still requires an inference step.

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?

No annotations are provided, so the description carries the full behavioral burden. The verb 'propõe' and the exclusion 'para alterar guias' imply a non-mutating planning operation, but the description does not disclose side effects, permissions, idempotency, or whether proposals are persisted.

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 two short sentences, front-loaded with the purpose followed immediately by usage and exclusion guidance. There is no filler or redundant information.

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 return values need not be explained. However, with six parameters, nested objects, an enum, and no annotations, the description does not explain what the tool computes from the inputs or how the input structures should be formed.

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%, and the description only repeats the required parameter concepts 'decisões' and 'guias'. It adds no meaning for optional keys such as id_key, status_key, operadora_key, or prestador_key, nor for nested decision fields like decision, motivo, or guia_ref.

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 ('Propõe') and resources ('decisões e guias'), so an agent can tell it is about proposing links rather than editing. It partially distinguishes from alteration tools via 'Quando não usar: para alterar guias', but it does not name a sibling or define what a 'vínculo' is.

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 explicit when-to-use context ('após ler um demonstrativo') and an explicit when-not-to-use condition ('para alterar guias'). It does not name the alternative sibling to use for alteration, so it falls short of full when/when-not/alternatives 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?

With no annotations, the description carries the full burden: it implies a read-only lookup but says nothing about permissions, pagination caps, or behavior when both CNPJ and CNES are supplied or when neither is. The existence of a `limite` parameter with a default and maximum hints at truncation behavior that is never disclosed.

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 short sentences, front-loaded with the purpose and followed by a use/don't-use delimiter that maps directly to agent decision points. Nothing 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?

An output schema exists, so return-value detail is not owed here. However, for a three-parameter lookup with zero schema descriptions, leaving `limite` and the both-optional key ambiguity unexplained means an agent can invoke it but may misuse the parameters.

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. It names CNPJ and CNES as the lookup keys but gives no format guidance (digits only vs. punctuation), no statement that at least one key is required, and never mentions the `limite` parameter at all.

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 ("Consulta as operadoras vinculadas a um CNPJ ou CNES") and immediately frames the scope as vínculos of an establishment. It also explicitly separates itself from the sibling operadora_lookup, so an agent can route without opening any 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?

Uses explicit when-to-use / when-not-to-use clauses and names the alternative tool (operadora_lookup) for the excluded case. This is the strongest possible routing guidance in a single sentence pair.

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?

No annotations are provided, so the description carries the full behavioral disclosure burden. 'Consulta' implies a read-only lookup, but the description does not state permission requirements, rate limits, or other operational constraints; the output schema covers return values but not safety context.

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 two sentences with no wasted wording. Purpose and the key usage constraint are front-loaded before the exclusion guidance.

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 return values need not be explained. The description covers purpose, primary use case, and alternatives, though it leaves the optional tabela parameter semantically unaddressed and provides no behavioral context beyond implying a read query.

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. It adds meaning for codigo as the TUSS procedure and for UF, modalidade, porte and semestre as comparison dimensions, but it does not explain the tabela parameter and gives no allowed-value guidance beyond schema patterns.

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: querying ANS D-TISS unit reference values by TUSS procedure. It also distinguishes the tool from operator-price and glosa use cases, so an agent can identify its role among siblings.

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 explicitly provides both 'Quando usar' and 'Quando não usar', including the alternative category: operator tools for glosa or contracted prices. The comparison dimensions UF, modalidade, porte and semestre are also named.

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?

No annotations are provided, so the description carries the burden. It discloses aggregation and privacy behavior (no raw guide data exposed, CPF pseudonymized), which is materially useful. It does not state read-only status, side effects, or performance/rate limits, so it is not fully transparent.

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 compact sentences with the aggregation behavior front-loaded, followed by explicit use/non-use routing. No filler, and both clauses earn their 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?

Purpose and routing are clear, and the output schema covers return values. However, for a tool with six parameters, nested objects, and zero schema descriptions, the definition leaves the agent without guidance on populating 'lotes', 'data', 'operadora', 'contexto', or 'regras'.

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% for six parameters, including the required 'lotes' array and nested 'contexto'/'regras' objects. The description only hints at pseudonymization (likely 'segredo_pseudonimo') and does not explain 'data', 'operadora', 'lotes' format, or when 'contexto'/'regras' are needed, so it fails to compensate for the coverage gap.

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 ('Agrega achados por prestador e mês') plus scope constraints ('sem expor dados das guias', pseudonymized CPF) and explicitly excludes individual guide lookup and batch correction. An agent can distinguish it from siblings like tiss_apply_fixes or parsing tools 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?

Includes explicit 'Quando usar' and 'Quando não usar' clauses that route rejection analysis here and individual guide queries / batch corrections elsewhere. It does not name the competing sibling tools directly, so routing is clear by task but not by exact tool name.

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?

No annotations are present, so the description must carry behavioral disclosure. 'Retorna' implies a read-only reference lookup, but no auth, rate-limit, or data-freshness behavior is described; the usage note adds context about when it is inappropriate but not about operational behavior.

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 sentences, front-loaded with the action and followed by use/exclusion guidance. No 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?

For a zero-parameter catalog tool with an output schema, the description is largely complete: it identifies the resource and clarifies when to use or avoid it. Return-value details can be left to the output schema, though catalog scope/freshness is not covered.

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?

There are zero input parameters, so the baseline is 4. The description correctly adds no parameter detail because there is nothing to parameterize.

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 ('Retorna') and resource ('catálogo SP/SADT'), making the core operation clear. It does not explicitly contrast with sibling tools such as tiss_sadt_missing, so differentiation is left to the resource name rather than spelled out.

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?

Provides explicit 'Quando usar' and 'Quando não usar' conditions, telling the agent to use it for knowing fields/domains and not for filling a guia without data. It does not name an alternative tool for the excluded case, but the usage boundary is 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?

No annotations are provided, so the description carries the full behavioral burden. 'Identifica' implies a read-only inspection, but the description never states whether it mutates anything, what happens with malformed or partial input, what the result granularity is, or any preconditions — notable gaps given the nested 'values' payload.

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 short clauses, front-loaded with the purpose and then the usage rules; no filler. Its terseness is efficient, though the extreme brevity leaves the payload shape unexplained.

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?

Placeholder for completeness.

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?

There is one parameter, 'values', a free-form nested object with empty properties and 0% schema description coverage. The description says nothing about what that object must contain (guide fields? SP/SADT block? full payload?), so an agent has no basis for constructing a valid call from either schema or description.

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?

Uses a specific verb ('Identifica') plus a precise resource ('campos obrigatórios SP/SADT ausentes'), so the agent knows this is a required-field completeness check rather than a full validator. It does not name the sibling it is contrasted with (presumably tiss_validate), which keeps it from a 5.

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 gives both directions: 'Quando usar: antes de renderizar uma guia' and 'Quando não usar: para validar um lote'. The exclusion usefully separates it from batch validation, but it stops short of naming the alternative tool to call instead (e.g., tiss_validate).

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses that the response is synthetic, but it does not explain side effects, whether any state is persisted, required inputs, or how the sandbox differs operationally from real TISS authorization tools.

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 a single concise sentence with no redundant text. However, it is under-specified for a three-parameter tool with a nested object rather than appropriately detailed.

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?

Although an output schema exists and need not be described, the tool has no annotations, 0% schema description coverage, and a nested 'solicitacao' object. The description is not complete enough to help an agent choose the tool confidently or supply parameters correctly.

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. It only vaguely references 'cenários disponíveis', which loosely maps to the 'cenario' enum, but it says nothing about the purpose or expected format of 'xml' and 'solicitacao', including the nested object.

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: it generates a synthetic SP/SADT response. It is clear enough to distinguish this as a sandbox/simulation tool from real authorization tools, though it does not explicitly name siblings or explain how it differs from tiss_autorizacao_build/check/parse.

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 no explicit guidance on when to use this tool versus alternatives such as tiss_autorizacao_build, tiss_autorizacao_check, or tiss_sandbox_enviar_lote. Usage is only implied by the word 'sintética' and the tool name.

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?

No annotations are provided, so the description carries the full burden. It signals this is a sandbox/simulation and constrains the protocol's origin, but doesn't state side effects, idempotency, or what error surfaces when the constraint is violated. Some behavioral context is added, but not rich.

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 clauses, front-loaded with purpose then when/when-not. Zero wasted words.

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 return values needn't be explained, and usage context is covered. Missing only behavioral details like read-only nature or error behavior for out-of-scope protocolos.

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% and no format for 'protocolo' (length, pattern, case) is described. However, with only one self-descriptive required parameter, the description adds marginal meaning via the 'same operadora' constraint. Adequate but not compensating fully for the coverage gap.

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?

Specific verb ('Gera') and resource ('demonstrativo de um protocolo simulado') clearly state what the tool does. It implicitly distinguishes itself from tiss_parse_demonstrativo (parsing) and tiss_sandbox_enviar_lote (sending), though it doesn't name siblings explicitly.

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 gives both the trigger ('após enviar um lote') and the exclusion ('com protocolo de outra operadora'). An agent has clear routing criteria to select or reject 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?

With no annotations, the description carries the full burden. It discloses the critical safety trait that this targets a simulated operator for local testing and not real data, but it does not describe side effects, how the scenario or attempt parameters affect behavior, or what happens to the submitted lot.

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 two short sentences with the core action front-loaded and immediate usage guidance following. Every clause is relevant and there is no wasted text.

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 return values need not be described. However, for a four-parameter tool with no annotations and 0% schema description coverage, the description is too thin: it omits parameter meaning and behavioral details an agent needs to invoke it correctly.

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% and the description does not explain any of the four parameters. It implies a batch is sent but does not clarify that 'xml' is the batch payload, nor does it add meaning for 'cenario', 'tentativa', or 'registro_ans' beyond what the bare schema shows.

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: 'Envia um lote à operadora simulada' (sends a batch to the simulated operator). It also distinguishes the sandbox context by mentioning local integration testing versus real data transmission, though it does not explicitly name sibling sandbox tools.

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 gives explicit when-to-use and when-not-to-use guidance: 'para testar integração local' versus 'para transmitir dados reais'. It does not name alternative tools or explain which sibling to use for other sandbox operations.

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?

No annotations are provided, so the description carries the full burden. It implies a non-mutating validation step and clarifies it is not the fix tool, but it does not disclose validation scope, idempotency, permissions, or whether any side effects exist. The usage cycle adds useful context but leaves meaningful behavioral gaps.

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 what the tool does, followed by when to use and when not to use it. It is short, structured, and every sentence has a clear purpose.

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 tool has five parameters, nested objects, and only 20% schema description coverage, with no annotations. The description covers purpose and usage well but leaves parameter composition and behavioral details incomplete for a tool of this complexity.

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 20% across five parameters, and the description mentions only XML and lote input forms. It does not explain data, contexto, operadora, or whether at least one input form is required, so it fails to compensate for the low schema coverage.

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: 'Valida XML TISS ou lote em JSON.' It also distinguishes validation from correction by referencing tiss_apply_fixes in the exclusion guidance, so the agent can separate it from sibling tools.

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 says when to use ('antes de gerar ou enviar um lote') and when not to use ('para corrigir achados sem aplicar o ciclo validar → tiss_apply_fixes → validar de novo'), naming the alternative workflow. This is strong 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?

No annotations are supplied, so the description carries the full behavioral burden. "Busca" and "exato" imply a read-only, exact-match lookup (no fuzzy results), which is useful signal, and the output schema covers the return shape. However, nothing is said about permission requirements, how tabela or include_expired alter the result set, or what an unmatched code returns.

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 clauses, zero filler, with the exact-match scope front-loaded before the when-to-use/when-not guidance. Every sentence earns 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?

The output schema exists, so return values need not be described. But for a 4-parameter tool with 0% schema coverage and no annotations, the description leaves three optional parameters and all behavioral caveats undocumented, which is a real gap for an agent building a correct call.

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% across 4 parameters, so the description must compensate and it largely does not. "Vigência" hints at the role of the data parameter, but tabela and include_expired (which materially change which codes are returned) are never explained.

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?

"Busca um código TUSS exato" gives a specific verb (busca) plus a precise scope qualifier (exato), which is exactly what distinguishes it from the fuzzy/description-based sibling tuss_search. The differentiation is stated in the text itself, so an agent never needs to open the schema to tell the two apart.

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 uses an explicit "Quando usar / Quando não usar" pair: use it to look up a code or its validity, do not use it for description-based search. Both the positive trigger and the exclusion route the agent to the correct sibling (tuss_search).

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?

No annotations are provided, so the description carries full behavioral burden. 'Busca' implies a read-only lookup, but the description discloses nothing about result limits, expiration handling, or whether the search is scoped by table/date – all of which exist as parameters. An output schema exists, so return shape needn't be described.

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 short, front-loaded sentences with no filler, and the use/avoid clauses are cleanly separated. It is arguably too terse given four undocumented parameters, but that is a completeness issue rather than verbosity.

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?

A 5-parameter tool with zero schema coverage, zero annotations, and a behavioral flag as significant as include_expired receives no explanation anywhere. The presence of an output schema removes the need to describe returns, but the input side is markedly under-specified.

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% across 5 parameters, and the description explains none of them. Only 'text' is loosely implied by 'por texto'; data, tabela, limite, and include_expired – including the non-obvious expired-code filtering – are left completely undocumented.

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 ('Busca códigos TUSS por texto'), so an agent knows exactly what it does. However, it gives no differentiation from the sibling tuss_lookup, which by name appears to cover overlapping territory.

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 provides 'Quando usar' (locate procedures by description) and 'Quando não usar' (validate XML), which is genuine routing guidance. It does not name the alternative tool (e.g. tiss_validate) for the excluded case, leaving the agent to infer it.

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