editalmd

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 token requirement, cost behavior (charged once), and how out-of-dictionary CNAEs appear (null family). However, it does not clarify whether this is a write operation (creates alerts), its side effects, or the response format beyond that one note. It adds some value but lacks depth, so a 3 is fair.

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, dense sentence that front-loads the purpose and then lists key behaviors. It is concise and information-dense without excess fluff. It could be broken into bullet points for readability, but it's well-structured and efficient.

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 should explain return values. It partially does by mentioning that out-of-dictionary CNAEs appear with null family in the response, but it does not describe the full response structure, error cases, or other behavioral details. For a tool with 5 parameters and no output schema, this is moderate but incomplete.

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 is 3. The description adds context about how CNAE activities relate to families and max_familias limits, which enriches understanding of parameters like max_familias. It does not introduce new syntax or format details beyond the schema, so it remains at baseline.

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 clearly states the tool's purpose: generating alerts for new purchases by company CNPJ. It specifies the verb ('Alertas de compra nova'), the resource (CNPJ), and the core logic (CNAE to families). It does not explicitly differentiate from siblings like 'alertas_compras' or 'criar_alerta', but the CNPJ-specific focus is evident. A 4 is appropriate because it's clear but lacks explicit sibling differentiation.

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 mentions a prerequisite (token edm_…) and cost implications (charging for overage), but does not provide guidance on when to use this tool versus alternatives like 'criar_alerta' or 'alertas_compras'. It also doesn't state when not to use it. The context is minimal, so score 2.

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 transparency burden. It discloses the required edm_… token and implies a pull/read-style operation, but it does not state whether the call is read-only, how the token should be supplied, or any pagination/error 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?

Two short, front-loaded sentences with no filler. The first delivers the core purpose and output characteristics, and the second adds the necessary auth condition. 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?

For a tool with only two parameters and no output schema, the description provides the essential invocation context: resource type, alert id applicability, response content hints, and token requirement. It would benefit from clarifying the response shape or the meaning of 'canal pull', but these are minor gaps for such a simple tool.

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 input schema already documents both parameters completely: id is 'id do alerta' and limite is '1 a 100 (padrão 50)'. The description adds no extra parameter-level meaning, so the schema-coverage baseline of 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?

The description identifies a concrete resource—purchases already matched to an alert—and gives scope qualifiers: pull channel, deadlines, and delivery status. It does not state an explicit verb like 'list' or 'obtain', and it does not directly distinguish itself from sibling tools, 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 clear contextual guidance: this is for purchases already matched with an alert via the pull channel, and it signals an auth prerequisite. However, it never explicitly mentions when to choose this tool over related siblings such as vigiar_compra, alerta_por_cnpj, or compra, nor does it state exclusions.

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 of behavioral disclosure. It reveals content categories but does not state whether the operation is read-only, what the output format is (e.g., JSON, text, markdown), or any other behavioral traits. This is a notable gap for an agent deciding whether invoking it has side effects or requires auth.

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 phrase with the key term 'Índice da API' front-loaded, followed by the main covered topics. Every word adds value and there is no redundancy or 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, no-output-schema tool, the description gives the essential content areas (routes, billing, price) but fails to specify what the actual response looks like or that it is a safe, read-only lookup. Given the simplicity of the tool, this is acceptable but leaves some ambiguity about the return format.

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 has zero parameters, so the baseline is 4. The description correctly makes no parameter claims, and the schema is empty. No additional parameter explanation is needed.

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 (API do EditalMD) and specifies the content (rotas, regime de cobrança e preço), clearly identifying it as an index of API information. It lacks an explicit verb like 'lists' or 'returns', but the noun 'Índice' conveys the action. It is distinct from all sibling tools, which are specific operational 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?

The description implies usage: consult this tool when needing API routes, billing regime, or pricing. It provides clear context but no explicit when-to-use or when-not-to-use instructions, and no alternatives are mentioned. Since no sibling tool serves the same index-looking purpose, the implied guidance is adequate.

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 of behavioral disclosure. It states the tool is 'Grátis' (free) and lists return fields, but it does not explicitly indicate that the operation is read-only or non-destructive. For an agent assessing safety, the lack of an explicit 'does not modify data' or 'read-only' statement is a significant gap. It also does not mention rate limits, authentication, or any 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?

The description is a single, efficient sentence that front-loads the action ('Busca compras públicas do PNCP por termo'), then adds a key behavioral trait ('Grátis'), and finally lists the return fields. There is no waste or redundancy. Every word earns its place, making it well-structured and concise.

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 covers the source (PNCP), the operation (search by term), and the return fields, which are the core elements. However, it does not mention pagination, how to retrieve more results, or explain the role of the 'limite' parameter beyond the schema. It also lacks guidance on how this tool relates to siblings like 'compra' or 'edital_markdown'. Given the absence of an output schema, a bit more detail on the result structure would enhance completeness, but it is sufficient for basic usage.

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 schema coverage is 100%, so all four parameters (q, uf, limite, abertas) are already documented with descriptions in the input schema. The description adds the concept of 'por termo' (by term) which relates to q, but does not deepen the meaning of uf, limite, or abertas beyond what the schema provides. Since the schema already carries the burden, a baseline of 3 is 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?

The description states a specific verb ('Busca' = searches) and a specific resource ('compras públicas do PNCP'), making the core purpose clear. It also lists the return fields (objeto, órgão, UF, modalidade, id), which adds specificity. However, it does not explicitly distinguish itself from sibling tools like 'compra' or 'edital_markdown', which could also be used for procurement-related lookups, so it falls 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?

The description implies when to use it (when searching by term) and notes it is free, but it does not provide explicit guidance on when not to use it or mention alternatives. There is no comparison to siblings or exclusion criteria. The usage context is inferred from the description rather than clearly stated, earning a middle score.

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 of behavioral disclosure. It partially does so by describing output components and the q/no-q behavior. Still, it does not state whether the operation is read-only, what the response shape is, or any error/edge-case behavior, and the garbled phrasing obscures the intended 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?

The description is very short but poorly structured as a run-on, with the confusing opening 'A lista de CNAE como o alerta por CNPJ a lê' preceding the more informative content. It is not clearly front-loaded and would be clearer as separate sentences.

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?

Given no output schema and no annotations, the description should provide a complete picture. It does mention key return fields and the ranking behavior, but it lacks a clear statement of the response type (list vs ranking) and the relationship with CNPJ alerts. This leaves some ambiguity for an agent deciding how to invoke it.

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 schema already documents q and limite well. The description adds meaningful semantics by explaining the effect of omitting q (ranking instead of filtered list) and explicitly ties q to code prefix or description word, going beyond the schema baseline.

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 identifies the resource as 'A lista de CNAE' and enumerates its contents (official IBGE description, family, dictionary terms, active SICAF suppliers), so an agent can grasp the basic purpose. However, the phrase 'como o alerta por CNPJ a lê' is vague and there is no clear verb or explicit differentiation from the sibling alert 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?

The description provides conditional behavior: 'Sem q, o ranking de quem mais vende para o governo' indicates that omitting q changes the result to a ranking. But it gives no guidance on when to use this tool versus the sibling alert/CNPJ tools, nor any exclusion criteria.

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. It adds a useful behavioral note ('Grátis') and describes the returned content, but it does not state read-only behavior, error handling, rate limits, or output format explicitly.

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 compact single sentence with the main output stated first and the cost note appended. It is efficient, though the meaning of 'ficha' could be more explicit.

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 simple one-id retrieval tool, the description is mostly adequate: it says what is returned and that it is free. However, without an output schema, it leaves the exact structure of the ficha and document list underspecified, and it does not mention how the id should be obtained beyond the schema note.

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%: id is documented as a number and as coming from the search, so the schema does the work. The description adds no parameter-specific meaning, 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?

The description names the resource (compra) and the output components (ficha, document list with extracted text and price), making the purpose clear even though the verb is implicit. It does not differentiate from sibling tools such as edital_markdown or vigiar_compra, so it does not reach 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?

No guidance is given on when to use this tool versus alternatives. The only directional hint, 'vem da busca' in the schema's id parameter, is not in the description and does not address sibling tools or preconditions.

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 disclosure burden. It clearly states that this is a one-time paid operation, the package amounts, and that the returned token is consumed by other APIs. It does not detail reversibility or failure scenarios, but the core side effect is 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?

The entire description is one efficient sentence with no filler. It front-loads the main action ('Recarrega crédito') and packs the payment method, package options, and return behavior into a compact structure.

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 tool with no output schema, the description explains the input values, the payment mechanism, and the return value (the token). It is slightly light on operational context such as how the x402 payment is executed or what errors may occur, but an agent can likely call 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?

The schema already documents the parameter well at 100% coverage, listing the valid values '1, 5, 10 ou 25'. The description adds the 'dólares' and 'pacotes' framing, which is helpful but largely redundant with the schema 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?

The description uses a specific verb ('Recarrega crédito') and identifies the exact resource and mechanism: paying via x402 in fixed dollar packages and receiving a token. This clearly distinguishes it from related siblings like credito_saldo, since it explains the recharge/token-return flow.

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 intended use is implied: an agent should call this to add credit before using other APIs. However, it does not explicitly state when to use this tool versus alternatives such as credito_saldo, nor does it mention when not to use it.

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 available, the description carries the burden and does disclose the key credential requirement (token 'cred_…'). It does not go further to state read-only behavior, rate limits, or error conditions, though 'saldo e extrato' strongly implies a safe query.

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, front-loaded sentence: the purpose comes first and the credential requirement is parenthesized. 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?

For a zero-parameter read tool, the description covers purpose and authentication in one line. It could also describe the response format or confirm that the call does not consume credit, but those are minor for a balance/statement 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?

The input schema has zero parameters, so there is nothing to document beyond the schema. The description correctly adds the only relevant context — the token requirement — rather than inventing parameter semantics.

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 clearly identifies the resource (prepaid credit) and the operation (returning balance and statement), so an agent can tell what the tool does. It does not explicitly contrast with the sibling credito_recarregar, but the sibling's name makes the distinction obvious.

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

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

It provides clear context: use this to inspect prepaid credit balance/extract, and it explicitly warns that a 'cred_…' token is required. It does not name alternatives or exclusion conditions, but no-argument usage makes the context sufficient.

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. It discloses the token requirement, channel behavior (pull reads via alertas_compras, webhook signs with whsec_…), and cost model. It does not describe side effects or post-creation responses, but covers essential behavioral expectations.

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 concise sentences front-load the purpose, then efficiently cover token, channels, and pricing without redundancy. Every clause adds 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?

Adequate for a creation tool with no output schema: it covers prerequisites (token), delivery methods, and costs. It doesn't explain the creation result (e.g., confirmation ID), but given the tool's simplicity and absence of output schema, this is 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 100%, so the schema already explains each parameter, including 'termos' syntax (space = all, | = any). The tool description adds no parameter-specific information beyond what the schema provides, meriting the baseline 3.

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 clearly states the tool creates a new purchase alert based on object terms and UF, differentiating it from siblings like 'alerta_por_cnpj' which is CNPJ-based. The verb 'criar' and resource 'alerta' are explicit.

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

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

Provides concrete context: requires an 'edm_…' token, lists three channels (pull, webhook, email) with specific mechanics, and mentions pricing (first free, others cost). It doesn't explicitly name alternative tools, but the purpose implies when to use this versus CNPJ-based alerts.

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 transparency burden. It discloses important traits: the token is displayed exactly once, the secret signs webhooks, and these credentials gate access to alert/vigia tools. It does not mention repeated-call behavior or recovery options, but the provided details are substantial.

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 filler, front-loads the core deliverable, and every clause adds useful information about the tokens, their purpose, or how to use them.

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 tool with no output schema, the description is nearly complete: it identifies the two generated secrets, their prefixes, their roles, and how to authenticate. It could be stronger by describing the exact response shape or error cases, but those are not critical for invoking it.

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 input schema has zero parameters, so there is no parameter meaning for the description to add. The baseline of 4 for zero parameters 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?

The description states a specific verb ('Cria') and two concrete resources: the edm_… owner token and the whsec_… webhook secret, along with their purposes. This clearly distinguishes it from siblings such as dono or rotacionar_segredo_webhook.

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 practical usage context: no registration is needed, the token is shown only once, and it must be sent as Authorization: Bearer in the alert and vigia tools. It does not explicitly compare against alternative tools, so it stops short of a 5.

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

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

With no annotations, the description carries the behavioral burden. It discloses the required auth token, the returned data (confirmed email, franchise, whsec_ secret), and the Standard Webhooks signing context. It does not explicitly state that the operation is read-only, but 'Estado do dono' implies a non-mutating lookup, and there is no contradiction.

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 dense sentence with no filler. It front-loads the core purpose and then packs the essential details: token requirement, returned state fields, and webhook signature behavior.

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 tool with no output schema and no annotations, the description adequately covers prerequisites and output semantics. It could also state the HTTP method or response format explicitly, but the essential information for calling and interpreting the tool 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?

The schema has zero parameters and 100% schema coverage, so there are no parameter details to document. The description adds value by clarifying the edm_ token requirement, which is an auth prerequisite rather than a schema parameter.

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 clearly identifies the resource ('dono') and conveys a status/lookup intent via 'Estado do dono', listing the relevant fields: confirmed email, franchise, and the webhook signing secret. It is distinguishable from siblings like criar_dono and rotacionar_segredo_webhook, though it lacks an explicit verb such as 'obter' or 'consultar'.

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 establishes clear context: this is the tool for reading owner status, and it requires an edm_ token. It does not explicitly name alternatives or exclusions, but the sibling set makes the distinction straightforward, and no competing status-lookup tool is present.

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 available, the description carries the behavioral transparency burden. It discloses the output format and a conditional access/pricing model, including that recent requests require x402 without registration. However, 'x402' is left unexplained, and there is no explicit statement about side effects or authentication beyond the payment note.

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 compact and front-loaded with the core purpose before the pricing nuance. Both sentences provide useful information, but the unexplained 'x402' and the dense pricing rule reduce overall clarity slightly.

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 endpoint with no output schema, the description covers the return format and an important access rule. It is sufficient for making a basic call, though it could be more complete by explaining 'x402' and clarifying the contents of the provenance front-matter.

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 input schema already covers the single parameter fully, explaining that `id` is the document id coming from `compra`. The tool description adds no additional parameter-level meaning, so with 100% schema coverage the baseline score of 3 is 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?

The description clearly identifies the resource (PNCP document) and the output format (markdown with provenance front-matter and hash). It is descriptive enough to distinguish the tool from siblings like `compra` or `recibo`. However, it lacks an explicit verb such as 'obtém' or 'gera', so the action is implied rather than stated.

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 cost-related conditions (free after 30+ days, paid per request if recent) but does not explain when to choose this tool over alternatives. No explicit 'use this when...' guidance or mention of sibling alternatives is provided.

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 behavioral disclosure burden. It does this well by disclosing that the tool is paid per document, accepts payment via x402 or credit, and does not charge again for the same text. It also describes what each returned item contains, giving useful behavioral context beyond the 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?

The description is two concise sentences with no filler. The first sentence states the core output, and the second adds critical billing behavior. Information is front-loaded and each 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?

For a one-parameter tool with no annotations and no output schema, the description covers the essential context: what is returned, the categories included, the literal excerpts, and the billing model. It could mention error/credit-shortage behavior, but this is a minor gap for a simple listing tool.

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%, and the single required parameter `id` is already described as 'id do documento (vem de `compra`)'. The tool description adds no further parameter-specific detail, so the baseline score of 3 is 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?

The description uses a specific verb and resource: it lists the habilitação sections of an edital, enumerating the categories (jurídica, fiscal/social/trabalhista, econômico-financeira, técnica) and stating that each item includes the literal text excerpt. This is clear and not a tautology, though it does not explicitly distinguish itself from siblings like edital_markdown or compra.

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 intended use is implied by the purpose statement — an agent would use this to retrieve qualification items for a given edital document. However, there is no explicit guidance about when to choose this over sibling tools, nor any mention of alternatives or exclusions.

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?

Não há anotações, então a descrição carrega o ônus de informar o comportamento. Ela diz que a ferramenta expõe saúde da origem e tamanho do acervo, o que sugere uma operação de leitura, mas não declara explicitamente ausência de efeitos colaterais, requisitos de autenticação ou formato de resposta.

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?

Uma única frase, direta, sem repetir o nome da ferramenta e com a informação essencial na frente. Não há desperdício.

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?

Para uma ferramenta sem parâmetros, sem schema de saída e de baixa complexidade, a descrição é suficiente para um agente entender o propósito e o conteúdo esperado. Detalhes como formato exato do retorno seriam úteis, mas não são críticos aqui.

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?

A ferramenta tem zero parâmetros, então o baseline é 4. Não há parâmetros para documentar e a descrição não precisa compensar lacunas de 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?

A descrição nomeia claramente o recurso: saúde da origem e tamanho do acervo, com escopo explícito (compras e documentos com texto). Falta apenas um verbo explícito como 'consultar' ou 'verificar', mas a intenção é compreensível e distinta dos irmãos.

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?

Não há orientação sobre quando usar esta ferramenta em vez das alternativas, como credito_saldo, api_index ou vigiar_compra. O contexto de diagnóstico fica implícito, mas não é explicitado.

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 behavioral transparency burden. It discloses that the impugnation deadline is estimated, explains the legal basis and calculation method, mentions national holidays, and states that the tool is free. This is meaningful context beyond the input schema, though it does not specify response format or error 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?

The description is extremely compact, front-loaded with the core purpose, and every part earns its place: what deadlines, how they are calculated, the legal reference, and the cost note. There is no fluff or redundant restatement of the tool name.

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 simple one-parameter lookup with no output schema, the description adequately covers what the agent will get back: the two relevant deadlines and their caveats. The only minor gap is not explicitly describing the response structure, but that is less critical given the straightforward content and the schema-covered input.

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%: the only parameter id is documented as 'id da compra (vem da busca)'. The tool description adds no additional parameter meaning, but this is acceptable because the schema already fully explains the parameter. Baseline 3 is 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?

The description clearly identifies the resource as 'prazos da compra' and enumerates two specific outputs: end of proposals and last day of impugnation. Though it lacks an explicit verb, the noun phrase strongly implies a retrieval operation. It is distinct enough from sibling tools like compra or buscar_licitacao by focusing on deadlines.

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 does not explicitly state when to use this tool versus alternatives such as compra or buscar_licitacao. It relies on the schema note that the id comes from the search, but gives no guidance on trade-offs or exclusions. Usage context is only implied by the tool name and the nature of the data.

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 behavioral burden. It explains what the receipt contains, which is useful context for a likely read-only lookup, but it does not explicitly state the operation type, authorization requirements, or possible 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?

The description is a single focused sentence that front-loads the resource and then lists the key return fields. 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?

For a simple one-parameter receipt lookup with no output schema, this description provides enough context: it names the output fields, and the schema supplies the id/header source. It could mention error conditions or response format, but those are not critical for basic 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 only parameter, id, is fully described in the schema, including its origin in the x-editalmd-recibo header. The tool description does not add extra meaning to the parameter, but with 100% schema coverage, the baseline of 3 is 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?

The description clearly identifies the domain (uma entrega), the deliverable (recibo), and its main contents (preço, modo de pagamento, hash). However, it uses a noun phrase rather than an explicit verb and does not directly contrast with 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?

The usage context is implied: the receipt is obtained from a delivery, and the id comes from the header x-editalmd-recibo. There is no explicit statement of when to use this tool instead of alternatives or when not to use it.

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?

There are no annotations, so the description carries the full behavioral burden. It discloses a key non-obvious behavior: the previous secret remains valid for 24 hours, allowing rotation without a failure window. This goes beyond the basic mutation implied by 'Troca' and is valuable for safe invocation.

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 redundancy. It front-loads the action, states the requirement, and follows with the important 24-hour grace-period behavior. Every word adds 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?

For a parameterless tool with no output schema, the description provides enough to understand the action, the prerequisite, and the grace-period behavior. It does not explain where the edm_… token comes from or what happens after 24 hours, but these are not essential for 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?

The tool has zero parameters and full schema description coverage, so there is no parameter documentation burden. The description still adds useful context by mentioning the required edm_… token, which an agent must provide through authentication rather than a parameter.

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 uses a specific verb ('Troca') and resource ('o segredo que assina os webhooks') to state exactly what the tool does. It is clearly distinct from the sibling tools, which focus on alerts, purchases, and credential queries rather than webhook secret rotation.

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

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

The description gives clear operational context: it is used to rotate the webhook signing secret and requires an edm_… token. It does not explicitly contrast with alternatives, but no sibling tool appears to offer the same functionality, so the absence of exclusion guidance is not a major gap.

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?

A descrição revela a exigência do token 'edm_…' e informa o tipo de dado retornado (eventos e fotografia atual). Como não há anotações, ela assume parte do ônus, mas não declara explicitamente que a operação é somente leitura nem eventuais efeitos colaterais ou paginação.

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 descrição é uma única frase objetiva, que empacota o conteúdo retornado e o requisito de autenticação sem rodeios. Informação essencial é apresentada de forma compacta.

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?

Para uma ferramenta simples, com dois parâmetros e sem schema de saída, a descrição cobre o recurso, o conteúdo retornado e o requisito de token. Faltam detalhes estruturais do retorno, mas a complexidade é baixa e as lacunas são aceitáveis.

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?

O schema já documenta 100% dos parâmetros ('id da vigia' e 'limite'), então a descrição não precisa repeti-los. Ela não acrescenta nenhum detalhe semântico além do que está no schema, ficando no baseline 3.

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?

O texto descreve claramente o objeto da ferramenta: eventos de uma compra vigiada e a fotografia atual. Apesar de não usar um verbo explícito como 'retorna' ou 'lista', a expressão nominal é específica e diferencia a ferramenta de irmãs como 'vigiar_compra' e 'compra'.

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?

A descrição indica implicitamente que a ferramenta deve ser usada para consultar o histórico de mudanças e o estado atual de uma compra monitorada. Porém, não menciona alternativas nem condições de uso em relação às ferramentas irmãs, deixando o agente inferir o contexto.

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

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

The description discloses that the tool 'fotografa agora' and 'registra eventos', which implies a state-changing side effect, and it mentions the cost implications for subsequent calls. It does not specify whether the tool is idempotent, what exactly happens after the first call, or what the response contains, but it gives enough behavioral context for a basic user.

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, compact sentence that packs multiple relevant details: the action, the required token, the event types tracked, and the pricing model. There is no redundant or filler wording, making it efficient and well-structured.

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 provides essential context like the token requirement, the events tracked, and the cost structure, which is useful for deciding to call the tool. However, it does not mention return values or how this tool relates to the sibling 'vigia_eventos' and 'alertas_compras' tools, leaving some contextual gaps for a fully informed 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?

All three parameters are described in the schema: canal is an enum with clear options, destino is explained as either an HTTPS URL or an email address, and compra_id is identified as the purchase ID from a search. The descriptions are minimal and do not clarify edge cases such as whether destino is required when canal is 'pull', but they cover the basic meaning of each parameter.

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 clearly states the tool's purpose: 'Vigia uma compra' and explains that it captures a snapshot and registers events such as rectification, new documents, suspension, deadline changes, and value changes. It also distinguishes itself by mentioning the required edm_ token and the pricing model, which helps clarify its role among the 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?

The description includes practical usage information such as the need for the edm_ token and the free-first-then-paid cost model, which guides when it is appropriate to call. However, it does not explicitly contrast this tool with siblings like 'vigia_eventos' or 'alertas_compras', so the when-to-use guidance is not fully explicit.

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