SEFAZ AC: NFC-e

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

The description goes beyond the annotations by explaining behavior in different modes: permanent config, session-only token login, and no-args link retrieval. It does not contradict the annotations, and it communicates that calling with no args does not authenticate but returns a link.

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 essential action, then uses 'Best' and 'Or' to structure the alternatives. Some phrasing like 'MCP.AI for IDE agents (Cursor, etc.)' is slightly noisy, but every sentence carries useful guidance.

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 authenticate tool with one optional parameter and no output schema, the description covers the main call variants and their outcomes. It does not describe error scenarios or response shape, but those are not clearly required given the low 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 schema provides only a bare 'token' string with no description, and schema description coverage is 0%. The description compensates by explaining that token is a JWT and that it can be passed after the user pastes it, while no args is also valid for retrieving the login link.

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: 'log in in the browser, copy the access token' and explains that calling with no args returns the login link. It also distinguishes this from other tools by framing it as the authentication/login tool for the server.

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 explicitly gives usage alternatives: adding the token as an Authorization header for permanent access, or passing { token: "<jwt>" } for a session-only login. It also says how to obtain the login link by calling with no arguments.

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 indicate read-only and idempotent behavior. The description adds specifics about output values (authenticated:true, pending[], connect_url) under different conditions, enhancing transparency beyond 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 concise, using two sentences to convey the core function and conditional outcomes. No unnecessary words 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?

Given the simplicity of a read-only, no-parameter tool, the description is fairly complete. It explains expected outputs under two scenarios, though it does not define 'pending' or list all possible states.

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 schema coverage is 100% and the baseline is 4. The description does not need to explain parameters and appropriately omits them.

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: returning connection status and URLs. It distinguishes from siblings by focusing on connection status, not authentication or marketplace 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 provides conditional behavior (when all providers connected vs. missing credentials) but does not explicitly state when to use this tool versus alternatives like authenticate. Usage guidance is implied but not direct.

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 indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds meaningful behavioral context beyond annotations: invoke has a one-off execution mode without bloating the toolkit, returns connect link if credentials needed, returns checkout/top-up link if wallet is empty, and writes (install/uninstall/subscribe/cancel and behind-the-scenes one-off install) require owner/admin. It doesn't contradict annotations. It stops short of describing all side effects or edge cases (e.g., exact failure modes of invoke), but given the broad scope this is solid.

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 dense and single-paragraph, but every sentence contributes to distinguishing marketplace from sibling tools. It uses 'KEY:' to front-load a critical constraint and clearly lists the PROMPT LIBRARY as a distinct feature. It could be improved with shorter paragraphs or bullet-like separation, but it is far from wasteful and the content justifies the length.

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 (23 params, 14+ actions), the description does a good job covering the main flow, auth/permission note, and special prompt library. It does not provide an output schema or explain return values, but each action's output is predictable given the narrative. It could add expected response shape per action or note that action defaults to 'search', which 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 0% and there are 23 parameters, so the description must compensate; it does name key parameters/actions (action, mcp_id, tool_id, arguments, prompt_* fields) and explains their role in a flow (search discovers MCPs by intent, describe returns profile, invoke RUNS tool with tool_id + params, publish_prompt returns shareable link). It doesn't itemize every parameter (e.g., request_details, report_context, cancel_reason) but maps the principal workflow, which is reasonable for a polymorphic action-based tool. What slightly holds back full marks: the description does not enumerate or explain the secondary parameters like conversation, immediate, tier_slug, cancel_reason, report_context.

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 names the resource (mcp.ai marketplace, in-platform catalog) and a verb family (search/describe/invoke/install...), and it distinguishes itself from sibling tools like authenticate/sefaz by clarifying its marketplace role. It specifies the core flow (action=search → describe → invoke) with clear semantics for each action (run one-off MCPs without installing, PROMPT LIBRARY too), so an agent can select it confidently.

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 strong selection guidance: use invoke for occasional/one-off use, install only for permanent toolkit addition, list_tools for callable-right-now, subscribe/cancel/report_bug/request_mcp for the other scenarios. It also states that writes require workspace owner/admin and explicitly cautions that invoke works even when the MCP is not installed, which helps the agent decide when to choose this tool over alternatives and what to expect.

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 indicate idempotent and non-destructive. The description adds no additional behavioral details beyond the instruction to include conversation for reproduction. It does not contradict annotations but also doesn't enrich understanding of side effects or permissions.

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, directly to the point, with no fluff. It states the action and the key parameter guidance efficiently.

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 reporting tool with no output schema arboretum, the description covers the purpose and the key reproduction parameter. It doesn't mention response or error behavior, but that's not critical given the tool's simplicity and the annotations provided.

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 description must compensate. It explains the 'conversation' parameter ('conversation array with recent messages') but does not describe 'message' or 'context'. It partially compensates but leaves some 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: 'Report a bug, missing feature, or send feedback.' This is a specific verb+resource and naturally distinguishes it from unrelated siblings like authenticate or marketplace.

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 guidance to include the conversation array for reproduction, which is helpful. However, it does not explicitly explain when to use this tool vs. alternatives or when not to use it, though siblings appear unrelated.

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 communicate readOnly, idempotent, and non-destructive behavior. The description adds value by disclosing the billing model, credential requirements, public-data nature, and LGPD responsibility, which are non-obvious behavioral and business traits.

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 most important fact: which query is being offered. Additional sentences cover credentials, payment, and legal context without making the description excessively long.

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?

Considering the simple single-parameter schema and the presence of annotations, the description covers the query's purpose, source, payment model, and non-confidential nature. It omits the expected response shape and exact NFC-e format, but remains mostly complete for this scope.

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%, and the description does not explain the expected format of the 'nfce' parameter or how an agent should provide it. The parameter name and tool name hint that it is a NFC-e reference, but the missing format is a real 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 begins with 'SEFAZ AC: NFC-e, consulta em fonte oficial', which explicitly names the resource (NFC-e), the jurisdiction (SEFAZ AC), and the operation (consultar). This clearly distinguishes it from generic sibling platform 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 states that the tool is platform-hosted, requires no platform credentials, is paid per query with prepaid credit, and uses official public Brazilian data. This gives the agent a clear context for when to use it, although no explicit alternative or exclusion is mentioned.

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, and openWorldHint=false, which fully conveys the safety profile. The description adds a small behavioral detail: it reports both 'platform' and 'adapter' versions, which is slightly more specific than the title. However, it doesn't detail output format or potential side effects (though unlikely for a read-only tool). Since annotations carry the transparency burden, the description's modest addition is acceptable, not perfect.

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, clear sentence that fully explains the tool's purpose. It is appropriately short for a zero-parameter, trivially simple tool. No unnecessary words 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?

Given the tool's extreme simplicity (no params, no output schema, no side effects), the description provides complete context. It tells the user exactly what information will be displayed. There are no missing pieces for a version-information 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?

With 0 parameters and 100% schema coverage, there is no parameter meaning to add. Per rubric, baseline is 4 when there are 0 params and schema covers everything. The description doesn't need to compensate for anything.

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 'Show the current MCP platform and adapter versions' clearly states the verb ('Show') and the resource ('MCP platform and adapter versions'). It is specific enough to distinguish itself from siblings like 'toolkit_info' and 'connect', though it does not explicitly contrast with them. The purpose is immediately understandable and 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 needing version info) but does not explicitly state when NOT to use it or name alternatives. Sibling tools like 'toolkit_info' might overlap, but no guidance is given on choosing between them. This earns a baseline 'implied usage' 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?

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, providing a strong safety profile. The description adds valuable context by specifying the exact contents of the returned state (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond what annotations reveal. It doesn't discuss potential costs or side effects, but that's not expected for a read-only tool with these 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 sentence that efficiently lists all key elements of the state information. It is front-loaded with the main verb 'Returns' and uses a colon to enumerate contents, making it easy to scan. Every element in the list earns its place; there is no filler 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?

Given the tool's simplicity (no parameters, no output schema, no nested objects), the description fully covers what an agent needs to know. It lists the main components of the state, and the read-only nature is already covered by annotations. There is no missing information that would hinder 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 schema description coverage is 100% (vacuous). The description correctly explains what the tool returns, which serves as the primary semantic content. Since there are no parameters to document, a baseline of 4 is appropriate because the description compensates by explaining the output.

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: it returns the current toolkit state, detailing installed MCPs, connection status, connected accounts, and catalog tool counts. This is a specific verb-resource combination that distinguishes it from siblings like show_version (which likely focuses on version info) and authenticate/connect (which are 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 implies the tool is used for getting an overview, but it does not explicitly state when to use it over alternatives. For instance, it doesn't mention that show_version might be more appropriate for version-specific queries. There is no when-not guidance, but the context is reasonably clear given the read-only nature and the sibling names.

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