SEFAZ AM: NFC-e

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

Annotations indicate non-read-only, idempotent, and non-destructive behavior. The description adds useful context about the browser login flow, permanent-vs-session persistence, and the input token being a JWT. It does not fully describe the response after token validation, but it discloses the key auth-mode behaviors.

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 short, front-loaded with the main login workflow, and contains little repeated or irrelevant text. It is slightly conversational but every sentence contributes to selecting and invoking the tool correctly.

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 one optional parameter and no output schema, the description covers the two invocation modes, the token source, and the persistence trade-off. It does not explain return values or failure cases, but the low complexity makes that a minor omission.

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 compensates fully for the only parameter: the 'token' is a user-pasted JWT, the exact expected call shape is shown, and the no-arguments case is explained as returning 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 identifies the tool's purpose: authenticating to MCP.AI and supplying an access token for IDE agents. It is more detailed than a simple 'Authenticate' statement, but it does not explicitly distinguish itself from siblings 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 actionable guidance: call with no args to get the login link, or call with a token for session-only login. It also contrasts session-only token entry with permanent config-based authorization, though it does not mention when to avoid this tool in favor of a sibling.

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 valuable state-dependent detail: what happens when all providers are connected versus when credentials are missing, and what fields appear in each case. 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?

Two sentences, front-loaded with the core purpose, and each sentence provides meaningful information without redundancy. Extremely concise 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 zero-parameter read-only status tool, the description fully covers the expected output in both plausible states. No output schema exists, so the description adequately carries the burden.

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 coverage is 100%. There is nothing to add beyond the description, and the baseline for zero-parameter tools is 4.

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 connection status and URLs, with specific conditions for authenticated vs missing credentials. This distinguishes it from sibling tools like authenticate, which likely initiates connections.

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 use for checking connection status and describes response states, but it does not explicitly state when to use it versus alternatives like authenticate or marketplace. No explicit when/when-not guidance is provided.

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

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

The description reveals behavioral details not in annotations: invoke runs tools without installing, returns connect/checkout links on missing credentials/empty wallet, write actions require admin permissions. It also explains the distinction between one-off invoke vs permanent install, and that publish_prompt returns a shareable link that opens without auth. These are significant runtime behaviors not implied by the annotations (readOnly=false, destructive=false, etc.).

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

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

The description is a single dense block that conveys a lot of information efficiently. It covers the main workflow, auth requirements, and the difference between invoke and install. While it could be broken into clearer sections, each sentence earns its place, so the length is justified.

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 with 14 actions and 23 parameters, the description provides substantial context: it explains the primary use cases, the distinction between permanent install and one-off invoke, auth failure behavior, and the prompt library. It does not detail every parameter or return value, but with no output schema, it offers enough guidance for an agent to operate effectively.

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 an overview of actions and mentions some parameters implicitly (action, mcp_id, arguments, prompt_* fields), but does not explain each parameter in detail. For 23 parameters with 0% schema coverage, it would be helpful to clarify specific fields like query, limit, tier_slug, and cancel_reason. However, the description does add meaningful context about the workflow (e.g., invoke requires tool_id, arguments; connect link on auth failure), earning a middle score.

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 marketplace as the official catalog and execution layer, with a specific verb for each action ('search, describe, install, invoke, subscribe/cancel, etc.'). It distinguishes itself from sibling tools by covering the full lifecycle of finding, running, and managing MCPs, and explicitly notes its scope ('every MCP/tool') versus connection or reporting tools. The description is unambiguous about what this tool does and its core workflow.

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 guidance: 'prefer invoke for a single/occasional use', 'use install only to make an MCP PERMANENT', and explains when to use list_tools, subscribe/cancel, request_mcp, etc. It also explains that invoke returns connect/checkout links and to retry after. This clearly differentiates from sibling tools like connect and report_bug.

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 read-only, idempotent, and destructive hints. The description adds useful context about including the conversation for reproduction, but does not disclose side effects, prerequisites, or post-report behavior beyond that.

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 contains no filler or redundant information.

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

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

For a tool with three parameters and no output schema, the description is incomplete: it fails to explain the 'context' parameter, mismatches the conversation format (array vs string), and does not state what happens after reporting. These are significant gaps for correct invocation.

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

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

Schema description coverage is 0%, so the description must compensate. It only partially explains 'conversation' as an array (though schema declares it as a string) and implicitly refers to 'message', while the 'context' parameter is completely unexplained.

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 with a specific verb ('Report') and resource ('bug, missing feature, or send feedback'), and the resource scope is distinct from the unrelated 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?

It provides clear context for when to use the tool (to report bugs/feedback) but does not mention explicit exclusions or alternatives. Since sibling tools are unrelated, the 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?

The description discloses that the operation is a query (read-only), requires payment via prepaid credit, and is from an official source. It also states that the data is not secret, which goes beyond the annotation hints. This exceeds the annotations' 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 relatively concise but contains some repetitive phrases about official sources. It is structured in multiple sentences but stays focused on the tool's purpose and conditions.

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

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

The description provides context about the tool's origin, payment model, and legal responsibility, which is sufficient for a high-level understanding. However, it lacks details on the expected output or additional usage specifics.

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 a single parameter 'nfce' of type string, but the description does not explain what this parameter represents. There is no description of the parameter's meaning, format, or constraints, leaving users without guidance on how to provide input.

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 is for consulting NFC-e (Nota Fiscal de Consumidor Eletrônica) from SEFAZ AM, an official source, and mentions it is a query operation. It provides enough context for a knowledgeable user.

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 usage guidance by indicating that prepaid credit is required, no platform credentials are needed, and it highlights the client's responsibility under LGPD for legitimate purpose. However, it does not specify exact scenarios or prerequisites beyond that.

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=false, so the safety profile is covered. The description adds the specific subject (platform and adapter versions) which is a useful detail beyond the annotations. No contradictions.

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, clear sentence with no fluff. It is perfectly concise 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 no-parameter, read-only informational tool, the description fully specifies what it returns. No output schema exists, but the tool's output is self-evident from the description.

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 zero parameters, and the schema coverage is vacuously 100%. The description doesn't need to elaborate on parameters, and the baseline for no parameters is 4.

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 resource ('current MCP platform and adapter versions'), clearly stating what the tool does. It distinguishes itself from siblings by focusing solely on version information.

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 or not use this tool, but it is a simple informational command. There is no comparison to siblings like toolkit_info, though the simplicity makes the use case obvious.

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 establish safety (readOnlyHint, idempotentHint), and the description adds value by detailing the specific data returned (installed MCPs, connection status, accounts, catalog counts). This goes beyond merely restating annotations, though it doesn't discuss edge cases like connection failures or performance implications.

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, well-structured sentence that front-loads the action and uses a colon to introduce a clear list of returns. Every word adds value, and the information is immediately scannable, making it an exemplar of conciseness.

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 introspection tool with no parameters and no output schema, the description is highly complete. It enumerates all key return aspects, leaving little ambiguity about what the agent can expect. It doesn't address potential error states, but given the tool's simplicity and non-destructive nature, this is not a significant 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?

With zero parameters, there is no schema coverage concern. The description effectively communicates the tool's purpose, and no parameter documentation is needed. The baseline of 4 applies due to the absence of parameters, and the description provides sufficient 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 uses a specific verb 'Returns' and clearly identifies the resource: 'current toolkit state' followed by a detailed list of components (installed MCPs, connection status, accounts, catalog tool counts). It fully distinguishes itself from sibling tools like 'show_version' or 'authenticate' by specifying the exact informational content.

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 its use case (checking toolkit state) but does not provide explicit when-to-use or alternatives. It doesn't exclude other tools nor direct the agent to a sibling for different needs. While clear on what it does, it lacks explicit guidance on when to choose it over 'show_version' or 'marketplace'.

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