ASTTEC: consultoria para negócios de bairro

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

No annotations are supplied, so the description carries the full burden. It does disclose a genuinely behavioral fact — the page is returned rendered as Markdown — and the verb "Devolve" signals a pure read with no mutation. It says nothing about authentication, rate limits, whether the returned content includes navigation/boilerplate, or how large pages behave.

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?

One short sentence, front-loaded with the verb and resource, with no filler. It is efficient but bare — there is no second sentence carrying routing or behavior 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 one-parameter read tool with a fully enumerated schema and no output schema, the definition covers the essentials, including the return format. It remains incomplete on sibling differentiation and on what the returned Markdown actually contains.

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 parameter is a closed enum with the label "Página desejada", so the schema already fully constrains the input. The description adds no meaning beyond it, which is acceptable at this coverage level but earns no credit.

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

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

The description names a specific verb ("Devolve") and resource ("uma página do site da ASTTEC") plus the output format (Markdown), so the operation is unambiguous. It does not, however, distinguish itself from siblings such as sobre_asttec or listar_segmentos, which could plausibly also return site content.

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 explicit guidance on when to choose this tool over listar_segmentos, pedir_diagnostico or sobre_asttec, and no note on prerequisites or when not to use it. Usage is only inferable from the tool name and the word "página".

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. It is a zero-parameter listing so the risk surface is inherently small, and the description does disclose the shape of the result (groups, their business types, and their page), but it says nothing about whether the catalog is static or account-specific, whether it is paginated, or whether any auth is needed.

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?

It is a single well-formed sentence with the verb and scope front-loaded, followed by the useful parenthetical enumeration of segment groups and a note on included fields. The parenthetical is long but each item is concrete content an agent could match a user query against, so it earns its space.

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 no output schema and no annotations, the description must describe return content, and it does so partially (segment groups, business types, page per group). For a zero-parameter discovery tool this is close to sufficient, with the main residual gap being ordering/format and whether the listed pages are directly consumable by ler_pagina.

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

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

The tool takes zero parameters, so there is no parameter meaning to add; the baseline of 4 applies. Nothing in the description misleads about inputs, and the empty schema is consistent with the description's claim of a global catalog listing.

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 specific verb plus resource ("Lista os grupos de segmento atendidos pela ASTTEC") and even enumerates the concrete segment groups covered, so an agent knows exactly what domain object this returns. It does not explicitly contrast itself with siblings like ler_pagina or sobre_asttec, though the resource is distinct enough that confusion is unlikely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the entry point for discovering which segment groups exist and which page each maps to, which pairs naturally with ler_pagina. There is no explicit when-to-use statement, no exclusions, and no mention of the sibling that would read the referenced page.

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 supplied, the description carries the full burden. It does disclose useful behavior beyond the schema: the request is filed on the owner's behalf with consent, and 'A equipe responde no contato informado' tells the agent a human team follows up via the given contact, which implies a real-world side effect. It does not state what the caller receives back (confirmation, request ID), how duplicate submissions are handled, or any failure modes – a notable gap for a write 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 short sentences, front-loaded with the action and recipient ('Registra ... o pedido ... da ASTTEC'), then the follow-up behavior, then the data-provenance restriction. Nothing is redundant, though the middle sentence about contact response could be folded into the schema note.

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 five-parameter mutation with no annotations and no output schema, the description covers purpose, authorization (consent), and the downstream response channel, which is what an agent needs before submitting. The missing pieces – confirmation/return behavior and duplicate or error handling – are modest but real gaps for a write operation.

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

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

Schema description coverage is 100%, so all five parameters (nome, negocio, contato, bairro, mensagem) are already documented in the schema; baseline 3 applies. The description adds only marginal meaning – that 'contato' is what the team will use to reply – but does not clarify the optional bairro/mensagem fields beyond the schema.

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 combination – 'Registra ... o pedido do diagnóstico gratuito da ASTTEC' – so the agent knows this submits a free-diagnostic request to ASTTEC. It is clearly distinct from the sibling read/info tools (ler_pagina, listar_segmentos, sobre_asttec), although it never names or contrasts those siblings explicitly, which keeps it below 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 gives meaningful usage constraints: act on behalf of the business owner, only with their consent, and 'Use só com dados que a própria pessoa forneceu' (only self-provided data). However, it offers no explicit when/when-not routing against the sibling tools and no prerequisites for calling, so the guidance is implied rather than fully specified.

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 burden, and it does establish that this is a fixed informational payload rather than a lookup that varies by input. It does not describe the return format, language, or whether the facts are static or cached, and 'planos do Chico' is left unexplained, which is a real ambiguity about what that section contains.

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 topic enumeration is dense but every item carries informational weight for an agent deciding whether to call. Slightly list-heavy phrasing rather than a clean statement of intent keeps it from a 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?

With no output schema, the description must signal what comes back, and the topic list largely does that for a zero-parameter info tool. The main gap is the unexplained 'planos do Chico' and no hint about response shape or size.

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

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

The tool takes zero parameters, so there is no parameter meaning to add; baseline 4 applies. Nothing in the description misleads about inputs, and additionalProperties: false confirms the no-arg contract.

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 the resource precisely (official ASTTEC facts) and enumerates the exact topics returned: what it does, target audience, how it works, plans, address, contact, and citation guidance. An agent can tell this apart from ler_pagina or listar_segmentos because it is a static institutional fact sheet rather than page retrieval or segment listing. It lacks an explicit verb and never names the siblings, so it stops short of 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?

Usage is only implied by the enumerated content: an agent can infer it should call this for questions about the company, its plans, address, or citation format. There is no statement of when to prefer it over ler_pagina or pedir_diagnostico, and no prerequisites or exclusions are given.

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