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

No annotations are provided, so the description must carry the full behavioral burden. It does not state whether this tool is read-only, whether it requires authentication or permissions, or whether calling it has any side effects. The phrase 'se lê ou grava' describes the method being inspected, not the behavior of this tool itself.

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, well-structured sentence that front-loads the core purpose and enumerates the key outputs without any 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?

The description is adequate for a simple lookup tool and the output schema covers return values. However, without annotations it should also clarify the tool's own safety profile and usage context relative to siblings, which it does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the single parameter 'nome' is already fully documented in the schema. The tool description adds no additional meaning or format details for the parameter, making the baseline 3 appropriate.

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 ('Detalha') and resource ('um método'), and lists the exact aspects returned: serviço, parâmetros, formato, e se lê ou grava. This clearly distinguishes it from siblings like listar_metodos and executar_metodo, which list or execute methods rather than describing one.

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 provides no explicit guidance on when to use this tool versus alternatives such as listar_metodos or executar_metodo. It only states what the tool does, leaving usage context 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?

With no annotations, the description carries the full burden, yet it discloses no safety profile (read-only? destructive?), permission needs, or idempotency. The one behavioral detail it does offer – what the response contains – is redundant with the existing output schema.

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. It is efficient, though arguably too terse given the absence of usage and behavioral context.

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 one param is covered. However, for a tool sitting among siblings like listar_telas and executar_acao_tela, the missing guidance on when to choose this one leaves a real 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?

The single parameter 'caminho' is fully documented in the schema (100% coverage), and the description adds no meaning beyond it. Baseline 3 applies when the schema does the heavy lifting for a one-parameter tool.

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 ('Detalha uma tela') and even names what the output contains (the fields it asks for and the available actions/buttons), which cleanly distinguishes it from listar_telas. It lacks explicit differentiation from siblings like executar_acao_tela, so it stops short of 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?

There is no when-to-use, when-not, or alternative routing. An agent must infer that this is the read/inspection step preceding executar_acao_tela or importar_arquivo_em_tela. Nothing tells it which sibling to pick.

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 a connectivity/credential probe but never states that it is read-only and side-effect free, whether it performs live network calls (and therefore may be slow or fail), or what it does when a component is down.

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 that front-loads the answer to 'what does this check' with zero filler or repetition of the title.

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, and with zero parameters the input side is trivial. However, with no annotations and no usage guidance, an agent still lacks the context to decide when this diagnostic is the right call versus 'diagnostico_web'.

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, which normally sets a baseline of 4, but there are no parameters here for the description to illuminate, and the description adds no invocation guidance (e.g. that no inputs are needed). The score reflects that the description neither helps nor harms on this dimension.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names what the diagnostic inspects — 'os dois web services, o catálogo e a credencial' — which is a concrete scope beyond the bare tool name, and the scope (two web services, catalog, credential) implicitly separates it from the narrower sibling 'diagnostico_web'. The verb is only implicit ('O que está de pé'), so it stops short of the specific verb+resource phrasing that would earn 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?

There is no statement of when to run this diagnostic, no preconditions, and no mention of the sibling 'diagnostico_web' that overlaps in scope. The agent must infer that this is a general health check 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, and it does disclose real internals: it logs in, counts menu screens, opens a sample, and verifies fields/actions, positioning itself as an alarm on panel changes. However, it never states whether the operation is read-only, what credentials/permissions it needs, or any side effects of logging in and opening screens.

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 the core check, then rationale (replay depends on panel shape), then the parameter hint — a logical order with little waste. Slightly longer than needed but every sentence carries 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?

For a single-parameter diagnostic tool with an output schema, the description covers purpose, internal behavior, and the alarm use case, so return-value explanation is rightly omitted. The only missing pieces are safety/permission context, which matters because it performs a login.

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 `caminho` parameter is already documented as 'Tela específica a conferir; senão, uma amostra.' The description adds a usage motive ('antes de uma operação importante') but no format, path syntax, or validity detail beyond the schema, so the baseline 3 applies.

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 (confere/faz login, conta, abre amostra) and resource (modo telas: login web, catálogo, forma das telas), and the goal (alarme se a Ahreas mudar o painel). It is distinguishable from diagnostic siblings like listar_telas/descrever_tela, though it never explicitly names `diagnostico` as the alternative.

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 one clear usage scenario — pass `caminho` to check a specific screen 'antes de uma operação importante nela' — but provides no when-not guidance or explicit routing versus the sibling `diagnostico` tool. Usage is implied rather than prescribed.

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 and does so well: it discloses the HTTP mechanism, the read/write safety split, the required confirmation flag, and the environment permission gate. It stops short of covering failure behavior or side effects beyond the write gate, so not 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?

Two compact, front-loaded sentences: the action is stated first, then the read/write rules. Nothing is padded, though the safety clause is dense enough that it reads as slightly compressed rather than a clean 5.

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 screen-automation tool with no annotations, an output schema present, and 4 fully documented params, the description supplies the critical missing layer: the write-authorization gate. An agent has enough to invoke it safely; only error/return nuance is absent, and the output schema covers returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so caminho, acao, campos, and confirmar are already documented; the description's 'preenche os campos e dispara o botão' and the confirmar rule largely restate the schema. Baseline 3 applies when the schema does the heavy lifting.

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 gives a concrete verb and mechanism: 'Aciona uma tela: preenche os campos e dispara o botão, por HTTP', which tells an agent exactly what happens. It implies the screen-vs-method distinction held by sibling executar_metodo, but never names or contrasts with any sibling explicitly, keeping it just short of 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?

It clearly partitions usage: read queries run directly, while mutating actions require confirmar=true plus the AHREAS_PERMITIR_ESCRITA flag, and it adds a workflow instruction to show the user what will run first. That is strong when/when-not guidance, though it doesn't name an alternative tool or say what to do for other 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?

With no annotations, the description carries the full behavioral burden and does well: it discloses credential use, read-versus-write behavior, a confirmation gate for writes and uncertain effects, and an environment-variable dependency. It omits error behavior, rate limits, and exact consequences when the write gate is disabled.

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 core action and immediately followed by the safety-gating rule. No filler or 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?

An output schema exists, so return values need not be explained. The description covers execution, credential scope, and write gating well, but omits discovery workflow guidance and details about the parametros object beyond what the schema provides.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline would be 3. The description adds real meaning beyond the schema for confirmar by saying it is required for methods that write OR have uncertain effect, and by tying writes to AHREAS_PERMITIR_ESCRITA.

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: executes an Ahreas method with the installation credential. It is clearly distinct from discovery siblings like listar_metodos and descrever_metodo, but does not explicitly name those alternatives.

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 operational usage conditions for confirmar: reads run directly, while writing or uncertain methods require confirmar=true and still depend on AHREAS_PERMITIR_ESCRITA. However, it does not say when to choose this tool instead of siblings such as executar_acao_tela or importar_arquivo_em_tela.

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 burden — and it does so well, disclosing the two-phase behavior (first call uploads and lets the screen recognize/populate fields without writing; second call with confirmar=true writes to the ERP) and the role of acao_processar as the writing button. It stops short of stating what success/failure looks like or permission requirements.

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-loads the core behavior, then metadata discovery, then the two-step confirmation flow. Emphasis markers aid scanning. Slightly verbose with parenthetical asides, but 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?

With an output schema present, return values needn't be described. The description fully covers the mutation semantics, the discovery prerequisites, and the confirmation workflow needed to call a 7-param write tool 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%, so the baseline is 3, but the description adds real meaning: it explains that acao_processar 'grava', that acao_reconhecer is the button the screen fires on acceptance, and frames confirmar as the write-enabling switch across the two-call flow. This goes beyond the schema's field-level text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Sobe um arquivo em QUALQUER tela de importação e, com confirmação, processa') and explicitly generalizes scope ('nada é específico de um fluxo'), differentiating it from per-screen siblings like executar_acao_tela. An agent can tell precisely what it does.

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 when-to-use and workflow: discover the screen via listar_telas and buttons via descrever_tela, call first WITHOUT confirmation and show the result, then call again with confirmar=true only after the person confirms. Names the sibling tools and the exact sequencing.

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, so the description carries the burden. It discloses the two-step discovery workflow (search by intent, then call descrever_metodo) and implies a read-oriented listing scope, though it doesn't spell out pagination or that some listed methods may write (only hinted via the apenas_leitura param). Adds real behavioral context beyond structured fields.

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-loads the key framing ('Passo 1 para...') and stays compact across three short blocks. Slightly noisy with all-caps emphasis and parentheticals, but each sentence carries routing or workflow value.

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 discovery/sequencing role is well articulated. Minor gap: it never clarifies whether listed methods include write operations, which matters for an agent deciding between this and listar_telas.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents busca, limite, and apenas_leitura. The description reinforces the intent-search pattern ('Busque pela intenção dela') but adds no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 ('listar_metodos') and frames it as 'Passo 1 para RELATÓRIOS e CONSULTAS financeiras' (web service), which clearly distinguishes it from the operating counterpart listar_telas. An agent can tell this is the discovery layer for data-oriented methods 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?

Explicitly states when to use it ('quando a pessoa quer DADOS: inadimplência, contas a pagar, fluxo de caixa...'), gives concrete intent keywords, names the alternative for operating (listar_telas), and prescribes the next step (descrever_metodo). Full when/when-not/alternative routing.

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 behavioral burden and does so well: it discloses the scope (383 screens), its role as step 1 of a multi-step workflow, and the hand-off to descrever_tela. It does not discuss permissions or result-size behavior, but the presence of an output schema covers return format.

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-loads the key framing ('Passo 1 para OPERAR...') and packs when-to-use, examples, fallback, and next step into three dense but readable sentences. Slightly example-heavy, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a listing tool with an output schema and full parameter coverage, the description supplies the missing workflow context: what it enumerates, when it applies, and where to go next. Return values are rightly left to the output schema; only edge details (paging via limite) go unmentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds search strategy beyond the schema's 'texto no nome da tela' — steering the agent to 'busque pela intenção' with examples ('consumo', 'boleto', 'emissão'). This makes the busca parameter's intended use clearer than the schema alone.

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 frames this as 'Passo 1 para OPERAR o Ahreas' and states it holds '383 telas da instalação', making clear it lists screens. It clearly distinguishes itself from listar_metodos (métodos vs telas). The listing verb is somewhat implicit — an agent infers it returns a set of screens — but the intent is unambiguous.

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 states when to use it ('quando a pessoa quer FAZER algo que se faz na tela'), with concrete examples (importar leitura, emitir boleto, gerar remessa), and names the fallback alternative ('quando listar_metodos não achou um método'). It even prescribes the next step (chame descrever_tela), leaving little to inference.

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