SEFAZ GO: NFC-e

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

The description discloses behavioral traits beyond annotations: the browser login flow, token persistence (permanent vs. session-only), and the no-args behavior that returns a link. It does not contradict the idempotentHint and destructiveHint 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 slightly lengthy but each part adds necessary information about the authentication flow and token options. It could be formatted with bullets for easier scanning, but it remains efficient and focused.

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

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

For a tool with only one optional parameter and no output schema, the description covers the main functional flow and expected outcomes well. It doesn't explicitly state the response format, but the instructions are sufficient for an agent to successfully invoke 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?

Even though the schema has 0% coverage and no parameter descriptions, the description fully explains the 'token' parameter: it expects a JWT string, is used when pasting a session token, and can be omitted to receive a login link. This completely compensates for the schema's lack of parameter documentation.

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 an authentication flow for MCP.AI within IDE agents, explaining the login process and token usage. It distinguishes itself from sibling tools by focusing specifically on authentication rather than connection or marketplace functions.

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 explicit usage instructions: add the token to config for a permanent non-expiring connection, or paste a session token, or call with no args to get the link. It lacks an explicit comparison with the 'connect' sibling tool, so alternate selection is not fully covered.

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 and non-destructive. The description adds behavior about return values under different conditions (authenticated:true, empty pending[], connect_url and per-install URLs), enriching understanding beyond the annotations. No contradictions 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 two sentences, front-loaded with the core purpose, and every word adds value. 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?

No output schema is provided, but the description fully explains the return shape in both scenarios (authenticated vs missing credentials). Given the tool's simplicity, the description is 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 input schema has zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and it does not introduce any confusion.

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: 'Returns connection status and URLs.' This specific verb+resource distinguishes it from siblings like authenticate and show_version, which have different purposes.

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 context on when the tool's output differs (when all providers connected vs credentials missing), but does not explicitly state alternatives or when to use this tool over siblings. This is clear context without exclusions, so a 4 is appropriate.

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 goes far beyond annotations, explicitly stating that writes require workspace owner/admin, that invoke runs one-off even when the MCP is not installed, that credential/payment failures return links for the user to act on, and that later retry may be needed. This gives strong, non-contradictory operational transparency.

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 long and dense, but every major subsystem of the tool is represented and much of the length is earned. The core flow is front-loaded effectively. It could still be improved with greater structural organization (e.g., bullets or clearer separation of MCP actions vs prompt library actions), but it is not bloated.

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 large, multi-purpose tool with 23 optional parameters and no output schema, the description covers the major areas thoroughly: the search/describe/invoke flow, installation semantics, billing/subscriptions, reporting, requesting new MCPs, and the prompt library. Credential/permission and payment retry behaviors are contextualized. Any residual gaps relate to unusually specific parameters rather than systemic missing context.

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 23 parameters and 0% schema description coverage, the description must carry the full explanatory burden. It successfully explains the main action values (search, describe, invoke, install, etc.) and links several fields to use cases (mcp_id, tool_id, arguments, prompt_slug, prompt_vars). However, many parameters such as limit, conversation, immediate, report_context, cancel_reason, and request_details remain unexplained, creating a clear 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 clearly identifies what the tool is and does: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It lays out a concrete core flow (search → describe → invoke) and distinguishes its many sub-actions from sibling tools like report_bug and show_version. The scope is explicit 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?

The description provides excellent usage guidance: use invoke for single/occasional use, use install only for permanent addition, and search/describe to discover MCPs. It also explains when to use the prompt library actions (search_prompts/get_prompt/publish_prompt) versus MCP actions, and covers credential/payment edge cases where the agent should retry.

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 disclose idempotency and non-destructiveness. The description adds the requirement to include conversation for reproduction, which is useful behavioral context. However, it does not describe what happens after reporting (async, response, etc.), so it adds only marginal value 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 two sentences, front-loaded with the purpose, then a concise instruction. No wasted words; it is efficient and well-structured.

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

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

For a simple tool (3 params, no output schema), the description covers core purpose and a key input behavior, but it omits explanations of the message and context parameters. While not catastrophic, it is not fully complete for an agent to invoke confidently.

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 mentions the conversation array but does not explain its format (string JSON) or default. It does not address the required 'message' parameter or the optional 'context' parameter, leaving most parameters under-explained.

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 reports a bug, missing feature, or sends feedback, which is a specific action on a clear resource. It distinguishes from sibling tools (authenticate, connect, etc.) which have unrelated purposes.

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 instructs to include the conversation array for reproduction, which is a usage guideline, but it does not explicitly define when to use this tool versus alternatives. Since no sibling overlaps, this is acceptable but still lacks explicit 'when not to use' or exclusionary 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?

The description adds meaningful behavioral context beyond annotations: it states no platform credentials are needed, queries are prepaid, data is non-confidential, and the client is responsible for LGPD compliance. This enriches the readOnly/idempotent/destructive hints already provided by 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 a four-sentence paragraph that includes both core purpose and legal/payment disclaimers. While not excessively long, the LGPD and payment details could be condensed without losing essential information. It is reasonably structured but less crisp than the high-scoring two-sentence examples.

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 query tool with one parameter, no output schema, and comprehensive annotations, the description covers key aspects: official source, payment model, privacy obligations, and non-confidential nature. It lacks explicit return-value details, but this is mitigatable given the query nature and no output schema requirement.

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 a single required parameter 'nfce' and zero schema description coverage, the description should compensate. It implies the parameter is the NFC-e identifier (from the tool name and context) but does not explicitly define its format, validation, or expected values. This adds some meaning but leaves room for ambiguity.

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 queries NFC-e (Nota Fiscal de Consumidor Eletrônica) from the official SEFAZ GO source. It uses specific verbs ('consulta') and identifies the resource, distinguishing it from sibling tools that handle platform management (auth, marketplace, etc.).

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 explicit guidance on when to use this tool versus alternatives. It mentions hosting and payment details but does not indicate prerequisites, exclusions, or situations where another tool should be preferred. The sibling tools are not referenced, and no alternative use cases are described.

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 'current' implying a live query, and specifies what is shown (platform and adapter versions). This adds useful context beyond the annotations, without contradicting them.

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

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

A single, concise sentence that clearly states the purpose. No wasted words or redundant details. It is well-structured and front-loaded.

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 version-check tool with no parameters and strong annotations, the description is complete. It doesn't specify output format, but that's likely a simple version string; given the low complexity, this 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?

There are no parameters (schema is empty). The baseline for 0-param tools is 4, and the description doesn't need to add anything about parameters. It correctly reflects that the tool takes no inputs.

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 is specific: 'Show the current MCP platform and adapter versions.' It uses a clear verb and identifies the exact resource (versions). It distinguishes from siblings like 'toolkit_info' or 'marketplace' because none of them explicitly mention versions.

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 when-to-use or alternatives are stated. However, given the tool's simple informational nature and that no sibling tool obviously serves the same purpose, the usage is implied: use when you need version info. It lacks exclusions but is adequate for a trivial 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 indicate readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context by specifying exactly what the tool returns, which goes beyond the annotations and clarifies the scope of this 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?

The description is a single, well-structured sentence that front-loads the main purpose and then uses a colon to list specifics. Every part adds useful information with 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?

Given the tool's low complexity—no parameters, rich annotations, and a clear read-only purpose—the description is fully adequate. It enumerates the key output categories even though there is no output schema, so an agent can predict what information it will receive.

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 there is no parameter burden for the description to carry. The description appropriately focuses on the output rather than inputs, and the schema provides complete coverage with no properties.

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: current toolkit state. It goes beyond a simple label by enumerating what is included—installed MCPs, connection status, connected accounts, and catalog tool counts—making it easy to distinguish from siblings 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?

The description clearly implies the use case: call this to inspect toolkit state and connection status. However, it does not explicitly state when to use this tool instead of a sibling like show_version, nor does it provide any exclusion or alternative guidance.

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