PagHiper

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

The description discloses that the tool initiates a browser login, returns a link when no token is provided, and performs a session login when a token is given. It also explains the JWT format and header configuration, adding significant context beyond the annotations (idempotent, non-destructive).

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 structured and front-loaded, starting with the core purpose and then detailing both permanent and session options using 'Best' and 'Or'. Every sentence adds value without redundancy, making it efficient yet comprehensive.

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?

While the description clearly explains how to invoke the tool and the two authentication modes, it does not explicitly state what the tool returns after a successful session login (e.g., a success message or token confirmation). Given the absence of an output schema, this is a minor gap, but the invocation guidance is sufficient for an agent to act 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 provides no description for the 'token' parameter (0% coverage), but the description fully compensates by explaining it is a JWT, how to use it for session login, and that omitting it returns a login link. This adds essential meaning beyond the raw 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 clearly states the tool's purpose: authenticating the user by logging into a browser and obtaining an access token. It explicitly differentiates between permanent configuration via headers and session-only login, effectively distinguishing it from sibling tools like 'connect'.

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 explicit usage instructions: calling with no args returns the login link, and calling with a token performs session login. It also recommends the permanent header configuration as a best practice, giving clear guidance on when to use each approach.

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?

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful behavioral nuance by detailing conditional return contents (authenticated:true with empty pending[] vs connect_url and per-install URLs), which is useful beyond annotation data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and every clause adds useful information about conditional responses. 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 status/read tool with strong annotations, the description fully covers the relevant behaviors, including response variation across connected and missing-credential states. No output schema is present, so explaining the return contents is sufficient.

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 100% schema coverage, so there is no parameter burden for the description to carry. The baseline for zero-parameter tools is 4, and the description appropriately focuses on behavior and outputs.

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 ('Returns') and clearly identifies the resource: connection status and URLs. It distinguishes itself from siblings like authenticate by describing its output modes (authenticated, pending, connect_url) rather than merely performing authentication.

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 situational context: when all providers are connected versus when credentials are missing, indicating when connect_urls are relevant. It does not explicitly name alternatives or exclusions, but the use case (checking connection status) is clear.

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

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

Highly transparent beyond the sparse annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description discloses the one-off invoke behavior (runs without install, no toolkit bloat), the connect-link flow for missing credentials, checkout/top-up flow for empty wallets, the retry requirement after the user acts, permission constraints (writes require owner/admin), and the installed_in_toolkit vs installed_in_workspace flags surfaced by search/describe. No contradiction with annotations; openWorldHint aligns with the multi-domain dispatch nature.

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 information-dense and every sentence carries genuine value, which is good for a 14-action composite tool. However, it is delivered as a single unbroken wall of prose with no paragraph breaks, bullet lists, or section headers, making it hard for an agent to parse the flow quickly. The opening does front-load the core purpose, but navigation through the MCP vs prompt-library sections requires careful reading. Appropriate length given complexity, but poor structural formatting.

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 the extreme complexity (23 params at 0% schema coverage, 14+ dispatch actions, no output schema), the description is remarkably complete: it covers the search→describe→invoke funnel, install/uninstall lifecycle, subscribe/cancel billing, report_bug/request_mcp channels, plus the entire prompt-library sub-domain including shareable login-free links. Minor gaps exist (the 'resume' action is never explained, tier_slug and subscribe tiering are unaddressed, cancel_reason semantics absent), but the description covers far more than would be expected for a tool this complex.

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

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

Schema description coverage is 0%, so the description carries the full burden of explaining 23 parameters. It names and gives semantics for the core ones (action dispatch with 14 values, mcp_id, tool_id+arguments for invoke, query for search, prompt_slug/prompt_vars for prompts). However, many parameters receive no semantic help at all: cancel_reason (with its enum), cancel_comment, report_context, request_details, tier_slug, immediate, conversation, prompt_targets, prompt_category, prompt_description. It compensates partially but not systematically for the 0% coverage.

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

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

The description clearly identifies this as the mcp.ai marketplace hub for discovering, profiling, invoking, and installing MCPs, plus a bundled prompt library. It specifies the verb+resource ('search discovers MCPs… invoke RUNS that tool') and distinguishes itself from siblings like connect, paghiper_* and toolkit_info. Minor deduction: the name 'marketplace' is generic and the description conflates two domains (MCP tools AND prompt library) under one tool, slightly muddying a singular purpose.

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?

Exceptional guidance. It explicitly maps the core flow (action=search → describe → invoke), names when to prefer invoke over install ('prefer invoke for a single/occasional use'), when install is required ('only to make an MCP PERMANENT'), distinguishes list_tools as 'what is callable right now', and gives the retry flow for auth/payment links. It also clearly separates the prompt-library sub-actions (search_prompts/get_prompt/publish_prompt). This is explicit when/when-not/alternatives guidance at a high level.

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?

Annotations are all false, so the description carries the burden. It adds meaningful context: no cancellation fee, only unpaid boletos can be canceled, and bulk execution is supported. This goes beyond the 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?

The description is compact and front-loaded: the main action is stated first, followed by fee information and bulk support. No unnecessary words or redundancy.

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

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

For a cancel operation with no output schema, the description covers purpose, condition (unpaid), fee, and bulk mode. It lacks return/error details, but the core is well enough specified.

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

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

The description explains transaction_id as the key and transaction_ids for batch, but it does not mention the account parameter. With 0% schema coverage, it partially compensates but leaves one parameter undocumented.

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

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

The description clearly states the tool cancels an unpaid boleto using transaction_id, specifying the exact verb and resource. The sibling paghiper_cancel_pix further distinguishes it as boleto-specific.

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 by limiting cancellation to unpaid boletos and mentions bulk support via transaction_ids. It doesn't explicitly name alternatives, but the 'ainda não pago' condition gives a clear when-to-use guidance.

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

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

Annotations include `destructiveHint: false` meaning it's not destructive, but the action is a cancellation which may have side effects. The description does not disclose what happens after cancellation (e.g., refund, notification), or whether it's reversible. Since annotations are neutral (no contradictions), the description adds minimal extra context, relying on the vague 'Cancela'.

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 long, concise, and front-loaded with the main purpose. Every sentence adds value: the first states the core action, the second mentions bulk support. No fluff 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?

The tool has 3 parameters, but the description only addresses two. No output schema exists, so the return value is not described. Annotations are sparse, and the description lacks details on prerequisites (e.g., charge must be unpaid) or error scenarios. Given its simplicity, it's minimally adequate but incomplete for full autonomous use.

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

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

Schema coverage is 0%, so the description must compensate. It explains `transaction_id` as the identifier and introduces `transaction_ids` for bulk, but does not explain the `account` parameter at all. While it adds some value for two parameters, the `account` parameter remains undocumented, and no format or examples are given.

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 action (cancel an unpaid Pix charge), specifies the resource (Pix charge), and includes the key identifier (`transaction_id`). It distinguishes itself from siblings like `paghiper_cancel_boleto` by targeting Pix specifically, though it doesn't name 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?

The description implies usage for canceling unpaid Pix charges and mentions bulk support via `transaction_ids`, but does not explicitly state when NOT to use it (e.g., for paid charges) or differentiate from `paghiper_cancel_boleto` beyond the resource type. No alternatives are named.

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

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

The description discloses that the tool creates a boleto and returns specific data, and mentions bulk behavior. It does not describe side effects, idempotency, or error conditions. With annotations having false values for all hints, the description carries moderate burden but covers only basic behavioral aspects, leaving some transparency gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct and well-structured: two short paragraphs covering the core functionality, key constraints, and bulk support. Every sentence adds value, with no redundant or irrelevant content, making it highly concise and easy to parse.

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 the tool's complexity (22 parameters, 11 required, no output schema), the description provides essential context: return values, minimum amount, address requirement, and bulk capability. However, it lacks explanations of parameter semantics, potential errors, or overall workflow, leaving gaps for agents needing full operational context. It covers the basics but not comprehensively.

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 description provides almost no parameter-level information. It only mentions that 'order_ids' is for bulk execution, but does not explain any of the 11 required parameters (e.g., payer_name, payer_cpf_cnpj, payer_street) or the meaning of optional ones. With 0% schema coverage, the description fails to compensate, leaving agents without clarity on parameter usage.

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 action ('Emite um boleto bancário registrado') and the resource (boleto), and specifies the return values (linha digitável, código de barras, URL do PDF, transaction_id). It also distinguishes itself from the Pix tool by noting the required full payer address, making its purpose 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?

The description implies when to use this tool (when issuing a boleto, not Pix) and provides key constraints: requires full payer address and a minimum value of R$ 3.00. It also mentions bulk support via order_ids, giving practical guidance. However, it does not explicitly compare with all sibling tools or state when NOT to use it beyond the Pix differentiation.

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?

Annotations only include readOnlyHint=false and others false, which are not very informative. The description adds value by specifying that CPF/CNPJ is required, minimum value, and that it returns specific fields, which gives the agent behavior expectations beyond the annotations. 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 concise and front-loaded with the main purpose and outputs. It adds essential constraints (CPF/CNPJ, min value) and bulk support in a compact way. No unnecessary 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?

With 14 parameters and no output schema, the description provides the core output structure and key constraints, but it doesn't explain optional parameters like shipping_methods or discount_cents, nor does it detail the payment flow. It is adequate but not fully complete for a complex 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 0%, so the description compensates by explaining key outputs and requirements, but it does not elaborate on individual parameters like discount_cents, days_due_date, or notification_url. It covers the core purpose but leaves many optional parameters undocumented.

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

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

The description clearly states the tool's purpose: emitting a Pix charge via PagHiper, and lists the specific outputs (pix_code.emv, qrcode_base64, qrcode_image_url, transaction_id). It distinguishes itself from siblings like paghiper_create_boleto by focusing on Pix and mentions required payer CPF/CNPJ and minimum value.

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 bulk support for order_ids, indicating a usage variant, but does not explicitly when to use this tool vs paghiper_create_boleto or paghiper_cancel_pix. It implies it's for creating Pix charges but lacks exclusions or alternatives.

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?

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful behavioral context beyond annotations: the supported status vocabulary and bulk execution via transaction_ids. It does not cover response shape or rate limits, but no contradictions exist.

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, front-loaded with the core purpose, and each sentence adds value—the status list and bulk-support note are both useful. No filler or redundant restating 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 read-only status tool with three parameters and no output schema, the description gives core semantics, statuses, and batch behavior. It is slightly incomplete because the optional account parameter is unexplained and the return structure is not described, but overall it is adequate.

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

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

Schema description coverage is 0%, so the description must compensate. It explains transaction_id as the lookup key and transaction_ids as the batch variant, but it omits the account parameter and provides no format or constraint details for the identifiers.

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 ('Consulta') and resource ('status atual de um boleto'), clearly identifying the tool's action. It enumerates possible statuses and is easily distinguishable from siblings like paghiper_get_pix_status and paghiper_cancel_boleto.

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 clearly indicates this is for boleto status lookup and notes bulk support via transaction_ids. It does not explicitly state when not to use it or name alternatives, but the resource scope is clear enough for selection among siblings.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description aligns with that by presenting a query-only operation. It adds the list of possible statuses and batch support, but it does not disclose any additional behaviors such as error conditions, response format, or account-scoping semantics. No contradiction exists between description and annotations.

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: one core sentence, a list of status values, and a single bulk-support sentence. It is front-loaded with the primary query key and avoids filler, making it easy for an agent to parse quickly.

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 read-only status tool with one required parameter and no output schema, the description covers the main query key, the statuses, and batch behavior. The mostly clear gap is the `account` parameter, but overall the tool context is sufficient for a human or agent to invoke it correctly.

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

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

With 0% schema description coverage, the description does some of the work by clarifying `transaction_id` as the query key and `transaction_ids` as useful for batch execution. However, `account` is left undocumented, and no constraints or relationship between the parameters are described, leaving a noticeable gap.

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

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

The description explicitly states the specific action: 'Consulta o status atual' (query the current status) of a Pix charge by `transaction_id`. It differentiates the tool from sibling status tools such as `paghiper_get_boleto_status` by naming Pix, and it enumerates the possible statuses, further clarifying its purpose.

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 makes clear that this tool is for checking live Pix statuses and mentions bulk behavior via `transaction_ids`, which gives useful usage context. It does not explicitly contrast with alternative tools like `paghiper_list_transactions` or `paghiper_get_boleto_status`, but the Pix-specific purpose is clear enough for selection.

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?

Annotations already declare readOnlyHint: true, idempotentHint: true, destructiveHint: false, covering safety. The description adds that it returns id and label, which is useful. However, it does not mention any other behavioral details, such as whether it requires prior authentication or any rate limits. Since annotations cover the safety profile, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that delivers the core information without extra fluff. It is front-loaded and efficient, with no 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 tool is simple, has read-only annotations, and no output schema. The description states it lists id and label, which is helpful. However, the unexplained 'account' parameter and lack of any usage context (e.g., whether it requires prior authorization) prevent it from being fully complete. It is adequate but with gaps.

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 one optional parameter 'account' (string) with 0% description coverage. The description does not mention or explain this parameter at all. With zero schema coverage, the description fails to compensate, leaving the parameter's purpose ambiguous.

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 verb 'Lista' (lists) and resource 'conexões PagHiper vinculadas a este install' clearly specify what is listed. It distinguishes from sibling 'paghiper_list_bank_accounts' by explicitly naming PagHiper connections and noting linked to this install. Clear and specific.

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 like 'paghiper_list_bank_accounts'. However, it implies it is for listing PagHiper accounts in this install, which gives context but no exclusions or alternatives.

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?

Annotations already declare the tool is read-only, idempotent, and non-destructive, so the description carries a lighter burden. The description adds the context of withdrawal destinations, which is useful, but does not disclose any further behavioral details (e.g., return format, pagination, or authentication requirements). Given the annotations cover the safety profile, this is acceptable.

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 sentence that is concise and front-loaded, clearly stating the tool's purpose without any extraneous information. It is appropriately sized for a simple listing operation.

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

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

The tool is simple (one parameter, no output schema), and the description explains its core function. However, the lack of parameter documentation is a gap, and there is no guidance on return values or usage context relative to siblings. It is minimally sufficient but not complete.

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 one parameter 'account' with no description and 0% schema_description_coverage. The description does not mention or explain the 'account' parameter at all. Since the description must compensate for the missing schema documentation but does not, the parameter semantics are inadequately conveyed.

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 lists bank accounts registered in PagHiper, specifying the resource (bank accounts) and the action (lists). It also adds context ('destinos de saque' / withdrawal destinations) that helps distinguish it from sibling tools like paghiper_list_accounts, which likely lists other account types.

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 when you need to see bank accounts for withdrawals, but it does not explicitly differentiate from sibling tools like paghiper_list_accounts or state when to prefer this tool. No when-not-to-use guidance is provided, so it's adequate but not explicit.

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 annotations already establish readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds behavioral value beyond the annotations by disclosing the default 90-day window and the available filtering modes (status and date interval), which are not present in the schema or annotations.

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 only two concise Portuguese sentences, front-loaded with the core purpose and followed by the key default behavior and filtering options. It contains no filler and does not restate information already in the schema enums.

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 read-only, idempotent list operation with no required parameters and good annotation coverage, the description covers the main call patterns: a plain call returning the last 90 days, a status-filtered call, and a date-interval call. It is complete enough for basic use, though the unexplained account parameter and missing date format leave minor gaps.

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?

With 0% schema description coverage, the description must compensate by explaining parameters. It does explain that status is a filter and that initial_date + final_date + filter_date form a date-interval grouping, which adds meaning beyond the raw schema. However, it leaves the account parameter and date format requirements unexplained, so parameter understanding is incomplete.

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 opens with "Lista as transações da conta PagHiper," a specific verb and resource that clearly identifies this as a transaction-listing operation. It is easily distinguishable from sibling tools like paghiper_get_boleto_status or paghiper_get_pix_status, which target individual payment items rather than the full account transaction set.

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 useful invocation context: without a date range, the API returns the last 90 days, and users can filter by status or a date interval. However, it does not explicitly contrast this tool with sibling status/account tools or state when not to use it, so usage guidance is implied rather than explicitly excluding alternatives.

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?

Annotations already cover readOnly=false and idempotentHint=true. The description adds useful context (including conversation for reproduction) but does not disclose potential side effects, such as whether the report is stored, transmitted, or triggers external actions. This goes slightly beyond annotations but lacks depth.

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-loaded with the tool's purpose, immediately followed by an actionable instruction. No redundant wording or fluff.

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

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

The tool is simple (3 params, no output schema). The description covers the core purpose and the most important parameter (conversation) but leaves 'context' unexplained and says nothing about what happens after reporting. This is sufficient for an uncomplicated tool with good annotations.

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 has 0% description coverage, but the description adds meaning for two of three parameters: 'message' (the bug/feedback content) and 'conversation' (the reproduction array). It omits 'context' entirely, so it partially compensates for the schema's lack of descriptions.

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?

Description clearly states the tool's action ('Report a bug, missing feature, or send feedback') with specific resources. It is distinct from all sibling tools (paghiper_*, authenticate, etc.), which handle unrelated operations.

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 implicitly defines when to use this tool (for reporting issues) and explicitly instructs to include the conversation array for reproduction. It does not mention alternatives, but sibling tools are unrelated, so no exclusion is needed.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds that the tool reports both platform and adapter versions, but it does not describe output format, network behavior, or whether any auth is required; this is acceptable for a simple read-only version tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise, front-loaded sentence with no filler. Every word contributes to explaining the tool's purpose.

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

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

This is a zero-parameter, read-only informational tool with strong annotations and no output schema. The description is sufficient for an agent to know exactly what information it will retrieve and that the call is safe; there are no hidden side effects or complex return values to document.

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 the schema coverage is 100%, so the baseline is 4. The description appropriately focuses on the result rather than inputs, and there is no parameter ambiguity to resolve.

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 function with a specific verb ('Show') and identifies the exact resources returned: current MCP platform and adapter versions. This distinguishes it from sibling tools like authenticate or paghiper_create_boleto, and while toolkit_info may overlap, the version-specific scope remains distinct.

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 provided about when to use this tool versus alternatives such as toolkit_info. The description implies a simple informational use case but does not state explicit context, exclusions, or alternative tool recommendations.

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?

Annotations already declare readOnly, idempotent, and non-destructive properties, and the description aligns by stating it returns state, which is a read-only operation.

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 concise sentence that fully describes the tool's function without 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 complete enough for a parameterless read-only query, specifying exactly what information is returned; no additional context is necessary.

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

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

There are no parameters, so the schema is fully covered; the description adds nothing needed since no parameters exist.

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 returns the current toolkit state, listing specific components (installed MCPs, connection status, accounts, catalog tool counts), which is distinct from sibling tools.

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

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

The description implies usage as a read-only status query, but does not explicitly mention when to use it versus alternatives; however, the intent is clear from its simple, parameterless nature.

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