SEFAZ PI: NFC-e

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

Description adds behavioral context beyond annotations: it explains the permanent vs. session-only distinction and that no args yields a link. Annotations already indicate idempotent and non-destructive, so the extra detail about auth modes is valuable. No contradiction found.

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 moderately long but every sentence contributes: it explains the process, the two alternatives, and the argument usage. It is front-loaded with the core purpose and structured logically, though slightly verbose for an authentication tool.

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 a single optional parameter and no output schema, the description covers all necessary aspects: the authentication flow, both invocation patterns, the target audience (IDE agents), and the meaning of the token. It is self-contained and adequate for an agent to call 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 fully compensates by explaining the token parameter: 'call with { token: "<jwt>" }' and 'with no args to get the link.' It clarifies that the token is a JWT and that omitting it requests a link. This is more informative than 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 function: 'MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token.' It distinguishes authentication from sibling tools by specifying the login flow and token handling. The purpose is specific and actionable.

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

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

Provides explicit guidance on two usage modes: 'Best: add it to this server's config as a header ... for a permanent, non-expiring connection' and 'Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.' This clearly instructs when to use each approach and how to invoke the tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the tool is known to be safe. The description adds value by detailing the response structure (authenticated, pending, connect_url) under different conditions, going beyond the annotations without 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 two sentences, front-loaded with the main purpose and then detailing conditional behavior. Every sentence provides necessary information without redundancy, making it highly 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?

With no output schema, the description fully conveys return semantics for both connected and missing-credentials cases. It covers the essential output fields and states, making it complete for a simple status 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 tool has zero parameters, so parameter semantics are trivially covered by the schema (100% coverage). The description doesn't need to explain inputs, and the baseline for zero parameters is 4, which is appropriate here.

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: 'Returns connection status and URLs.' It uses a specific verb (returns) and resource (connection status, URLs), and distinguishes itself from siblings like authenticate by focusing on status rather than authentication actions.

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 explains conditions (when all providers connected vs credentials missing) but does not explicitly say when to use this tool instead of alternatives like authenticate or show_version. It implies usage for checking connection status but lacks explicit guidance on 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?

The description discloses key behavioral traits: invoke works even when MCP is not installed (runs one-off without bloat), returns connect link if credentials needed, returns checkout/top-up link if wallet empty (then retry). It also notes writes require workspace owner/admin, and search/describe flag installed status. Annotations only provide readOnlyHint=false and destructiveHint=false, so the description adds critical behavioral details beyond annotations. No contradiction detected.

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 dense single paragraph but well-organized with semantic flow: purpose → core flow → key behaviors → action distinctions → additional catalog features. Every sentence adds new information. However, it is over 400 words, which might be long for quick scanning. The structure is logical but could benefit from bullet points for readability. Still, it is efficiently written with no filler.

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

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

Given the tool's high complexity (14 distinct actions, 23 parameters, multiple sub-systems like marketplace and prompt library), the description is remarkably complete. It explains the main workflow, edge cases (not installed, credentials, wallet), authorization requirements, and the difference between marketplace tools and prompt library. It even clarifies that invoke performs a one-off install, and search/describe flag installed status. The absence of an output schema is mitigated by mentions of return behaviors (connect link, checkout link, shareable link). The description covers virtually all contingencies.

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 0% description coverage, and the parameter list is extensive (23 params). While the description does not explain individual parameters, it explains the action enum values in context (search, describe, invoke, install, etc.), which is the most critical parameter. It also mentions the 'arguments' parameter implicitly by saying 'invoke RUNS that tool' with parameters. For parameters like mcp_id, tool_id, prompt_slug, the description provides enough context to infer meaning. The description adds value beyond the schema by clarifying which parameters to set for each action, especially the 'arguments' JSON structure. Given the huge parameter count and zero schema description, a score of 4 is justified as it compensates partially but doesn't detail every 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 as the official mcp.ai marketplace, covering both catalog discovery and execution of MCPs. It explains the core flow (search → describe → invoke) and distinguishes the tool from siblings like sefaz_pi_nfce_consultar and show_version. The verb ('marketplace' with action parameter) and resource are explicit, and the description provides specific examples of capability requests, making the purpose unmistakable.

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 guidance on when to use invoke vs install, stating 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It also explains when to use search_prompts/get_prompt/publish_prompt for the prompt library, and lists other actions like subscribe/cancel/report_bug/request_mcp. Distinguishes between the marketplace's own tools and external MCPs, clarifying usage context.

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 include idempotentHint: true and destructiveHint: false. The description adds the context that the request is for reproduction, which hints at behavior (conversation data is sent), but doesn't disclose outcomes like confirmation or error handling. It neither contradicts nor significantly enriches the annotation cover.

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 crisp sentences: the first states the action, the second gives a key usage hint. Every word earns its place with no filler. Excellent front-loading of primary 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?

For a simple bug-report tool (3 parameters, no output schema, clear annotations), the description is adequate. It covers what it does and a critical aspect of how to use it. A bit more detail on the return value or side effects would be nice, but not necessary for this simplicity.

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. It does explain that 'conversation array' is for 'reproduction', adding meaning beyond the schema. However, 'context' and 'message' parameters receive no explanation, so compensation 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 clearly states the purpose: 'Report a bug, missing feature, or send feedback.' This specific verb+resource combination (report + bug/feedback) distinguishes it from sibling tools like 'authenticate' or 'show_version'. No ambiguity.

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

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

Usage is implied: when you want to report an issue. The instruction 'Include the conversation array with recent messages for reproduction' gives a concrete guideline, but there's no explicit when-not-to-use or mention of alternatives among siblings. It meets the 'implied usage' bar (score 3).

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, idempotentHint, and destructiveHint. The description adds valuable behavioral context beyond annotations: hosted by the platform, no platform credentials needed, pay-per-query with prepaid credit, data is not confidential, and the client is the data controller under LGPD. This meaningfully informs the agent about authentication, cost, and data responsibility.

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

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

The description is front-loaded with the core purpose and uses four concise sentences, each adding relevant context: official source, hosting/payment, data classification, and LGPD responsibility. It is slightly dense but not wasteful.

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

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

For a simple one-parameter tool with good annotations, the description covers purpose, source, payment, credentials, and data privacy. However, it lacks input format guidance for 'nfce' and does not describe expected output or error behavior, which leaves some ambiguity for an agent invoking the 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 must compensate for explaining the 'nfce' parameter. It only implies that the parameter is an NFC-e identifier from the tool name and first sentence, but it does not specify the expected format, length, or any constraints. This is a significant gap for correct invocation.

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 tool as a consultation of NFC-e through the official SEFAZ PI source, using a specific verb ('consulta') and resource ('NFC-e'). It also distinguishes itself from unrelated sibling tools like authenticate, connect, and marketplace by focusing on official tax document consultation.

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 clear context for use: it queries official Brazilian sources available to citizens, requires no platform credentials, and is paid via prepaid credit. It does not explicitly name alternatives or exclusions, but the sibling tools are unrelated, so the usage context is 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context by specifying that the tool returns current platform and adapter versions, which is not present in the 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 a single concise sentence that is front-loaded and contains no unnecessary words. It fully communicates the tool's purpose without 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?

Given the tool's simplicity, no parameters, and rich annotations, the description is nearly complete. It states what information is returned (platform and adapter versions), though it does not specify the exact output format, which is acceptable for this level of complexity.

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

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

The tool has zero parameters and the schema is empty, so the baseline for parameter semantics is 4. The description does not need to compensate for parameter documentation gaps.

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 ('Show') and a specific resource ('current MCP platform and adapter versions'), clearly distinguishing this tool from siblings like authenticate, connect, and report_bug. It leaves no ambiguity about what the tool does.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. For a simple version tool this is somewhat implied, but there is no explicit usage context.

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 no further behavioral details (e.g., side effects, rate limits), but aligns with the annotations and clarifies the read-only nature implicitly.

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 clearly conveys the tool's purpose and return content without unnecessary verbosity.

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

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

Without an output schema, the description provides a reasonable list of returned information (installed MCPs, status, accounts, catalog count). However, it lacks details on the structure or format of the response, leaving some ambiguity.

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 no parameters, so the description correctly omits any parameter details. No additional semantics are needed beyond the empty 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 returns the current toolkit state and enumerates specific data points (installed MCPs, connection status, accounts, catalog tools count). This distinguishes it from sibling tools like show_version or authenticate.

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 explicit guidance on when to use this tool versus alternatives. It does not mention use cases, prerequisites, or conditions where it should be preferred over other status/version tools.

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