SEFAZ RN: NFC-e Resumida

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

It explains the permanent vs session-only behavior and that calling with no args returns a link. It also clarifies the token as a JWT. This goes beyond the annotations (which only indicate idempotent, non-destructive, not read-only) and provides useful context.

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, elongated sentence with multiple semicolons, combining several distinct pieces of information. It's not overly verbose but could benefit from clearer sentence breaks. It still covers essential points 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?

Given the single parameter, there is no output schema, and the description covers both invocation modes, the purpose of the token, and the no-args behavior. It is sufficiently complete for an agent to use the tool 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?

There's zero schema coverage, so the description must define the 'token' parameter. It does so, calling it a JWT to be pasted, and explains the effect of providing or omitting it (session login vs retrieving link). This adequately compensates for the missing schema 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 states it is for authentication: 'log in in the browser, copy the access token'. This is a specific verb and resource, and it distinguishes this tool from its siblings (which are unrelated).

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 gives explicit best practice ('Best: add it to this server's config as a header') and two distinct invocation modes: with a token for session-only login, or with no args to get the link. It doesn't explicitly mention when not to use it, but there are no similar sibling tools to confuse it with.

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 operation as read-only, idempotent, and non-destructive. The description adds useful behavioral context by specifying conditional outputs (authenticated:true with empty pending[] vs connect_url and per-install URLs), going beyond what the annotations alone convey.

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 concise sentences with the primary purpose front-loaded in the first sentence. It includes conditional details without any filler or redundant restatement 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 zero-parameter status tool with no output schema, the description covers the all-connected and missing-credentials cases adequately. It does not describe partial connection states or the exact structure of pending/URLs, but the overall context is sufficient for an agent to understand the tool's main behavior.

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 there is no parameter semantics burden on the description. The baseline of 4 is appropriate because no additional parameter detail is needed.

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') with a clear resource ('connection status and URLs'), and it distinguishes the tool from the sibling 'authenticate' by focusing on status reporting rather than initiating authentication. The conditional behavior reinforces 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 clear context for when to use the tool: to check whether all providers are connected or to obtain connect_urls when credentials are missing. It does not explicitly name alternatives or exclusions, but the conditions described give sufficient usage guidance for a status-checking 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?

With annotations present (readOnlyHint=false, destructiveHint=false), the bar is lower, but the description dramatically exceeds it by adding rich behavioral context: invoke works 'even when the MCP is NOT installed' as a one-off without bloating the tool list; credential needs return a connect link while empty wallets return a checkout/top-up link with a retry instruction; writes require 'workspace owner/admin'; and search/describe flag installed_in_toolkit vs installed_in_workspace. No contradiction exists — the description complements the annotations rather than repeating 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?

Every sentence earns its place — there is no filler or redundancy — but the description is a single dense wall-of-text paragraph that jumps across multiple domains (MCP discovery, one-off execution, wallet/auth handling, billing, bug reports, prompt library). The prompt-library section is a substantial tangent that could derail an agent scanning for search/prompts behavior. Appropriate density for the complexity, but the lack of any structural breakdown makes it harder to parse than it needs to be.

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 — 14 actions, 23 params, no output schema, no nested objects — the description is remarkably complete. It explains the core flow, the surprising invoke-without-install behavior, auth/wallet failure modes with retry semantics, administrative permission requirements, billing operations, and the separate prompt library with its own flow. Since no output schema exists, the description correctly conveys return behaviors (connect links, checkout links, shareable prompt URLs). Little is left unexplained for an agent to make a 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?

With 0% schema description coverage across 23 parameters, the description carries the full burden and compensates well: it explains action enum values manually, ties mcp_id/tool_id/arguments to the search→describe→invoke flow, connects prompt_vars to '{{variables}} filled' in get_prompt, and prompt_slug to the shareable mcp.ai/p/<slug> link. However, several parameters remain unexplained (immediate, tier_slug, conversation, report_context, prompt_targets, limit), so it doesn't fully close the coverage gap — but it goes well beyond a baseline for a tool this complex.

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 a specific, unambiguous statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then spells out the core flow (search → describe → invoke) and explicitly enumerates every action (install, subscribe, report_bug, request_mcp, search_prompts, etc.), making it impossible to confuse with its siblings (authenticate, show_version, toolkit_info). The verb+resource+scope are all clearly defined and heavily differentiated 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 gives explicit prescriptive guidance: 'USE install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It lays out a clear decision flow (search discovers → describe returns profiles → invoke runs), names when to use request_mcp ('when nothing fits'), and distinguishes the prompt library from MCP tooling ('search_prompts finds one, get_prompt returns its full text'). Alternative tools are explicitly named and contrasted, which is the gold standard for usage 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 states it reports a bug or sends feedback, which is a side-effectful action. It does not conflict with annotations (readOnlyHint false, destructiveHint false). It adds the requirement to include conversation, but doesn't detail what happens to the data. Given annotations exist, it's fairly transparent.

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 to the point, but it lacks structure and could benefit from clarifying parameter usage. It's one sentence, acceptable but not detailed.

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?

Provides some context about including conversation array, but doesn't describe the output or behavior beyond reporting. Also lacks explanation for other parameters and no output schema, so agent might not know what to expect.

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 3 parameters with 0% coverage in description. Only the conversation parameter is mentioned, while 'context' and 'message' are not explained. The required 'message' parameter is implied by the purpose, but 'context' 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 purpose: report a bug, missing feature, or feedback. The verb 'report' is specific, and the resource (bug/missing feature/feedback) is explicit. It is clearly distinguishable from siblings like authenticate or connect, which serve different 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?

It provides usage guidance by instructing to include the conversation array for reproduction, which implies when to use (when you have recent messages). However, it doesn't explicitly mention when not to use or compare with alternatives, but the purpose is clear enough.

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 provide readOnlyHint, idempotentHint, and destructiveHint. The description adds useful context: pay-per-query with prepaid credit, no platform credentials, and the note that the data is public/non-confidential and the client is responsible under LGPD. This goes beyond what annotations state.

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 front-loads the main purpose clearly but then includes several trailing clauses about hosting, credentials, billing, LGPD, and data control. These are relevant context but are packed densely, making the description less scannable than needed.

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 and a sparse parameter schema, the description should cover what the tool returns or how the input key works. It instead focuses on contractual and payment details. It gives a rough sense that the tool returns a summary, but not enough for an agent to correctly prepare the request or interpret the result.

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 parameter, 'nfce', with no schema description, and schema_description_coverage is 0%. The description mentions 'NFC-e Resumida' but never explains what string the parameter expects (e.g., access key, protocol, formatted number), provides no format, and no example. The description does not compensate for the missing 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 a consultation ('consulta') of 'NFC-e Resumida' from 'SEFAZ RN', with a specific source. It also distinguishes itself from the generic sibling tools like marketplace or show_version. It could be a 5 if it explicitly stated what the response contains, but the verb+resource is clear.

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 operational details (prepaid credit, no platform credentials, LGPD responsibility) but lacks explicit guidance on when to use this tool compared to alternatives. It does not state a scenario or say 'use this when...' or what other tools would be suitable instead.

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 and idempotentHint=true, indicating a safe read. The description adds specificity by naming 'platform and adapter versions' as the output content, but offers no further behavioral notes like authentication or return structure. Given annotations cover safety, a 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, front-loaded sentence with no wasted words. It conveys exactly what the tool does without 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?

For a zero‑parameter, read‑only tool with no output schema, the description is fully sufficient. It states what is retrieved (platform and adapter versions), and the annotations cover safety and idempotency.

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 the schema fully covers parameter structure. With no parameters, the description need not add parameter-specific detail, and the baseline of 4 applies per the scoring rubric.

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 verb 'show' and the specific resource 'current MCP platform and adapter versions.' It distinguishes from sibling tools like 'toolkit_info' by focusing narrowly on version information rather than broader system info.

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 on when to use this tool versus alternatives. There is no mention of scenario context (e.g., checking version compatibility) or exclusions. The description only states what it does, not when to use it.

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 and destructiveHint=false. The description adds value by detailing what 'state' includes (installed MCPs, connection status, accounts, catalog tool counts), which is consistent with the read-only nature and gives the agent a full behavioral picture without being prompted.

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, front-loaded sentence that names the resource and immediately lists the key data points. Every word is informative, 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?

For a zero-parameter, read-only status tool, the description is complete. It explains exactly what information will be retrieved (installed MCPs, connection status, connected accounts, and catalog tool counts), which is sufficient for an agent to decide when to call this 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?

Tool has zero parameters, so schema coverage is 100% by default. The baseline for 0 params is 4, and the description does not need to add parameter details. Nothing is missing.

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 defines the resource as 'current toolkit state', then enumerates the exact contents (installed MCPs, connection status, accounts, catalog tool counts). This fully differentiates it from sibling tools like authenticate, connect, and marketplace, which imply authentication and connectivity 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 gives clear context of what the tool does and what it returns, making its use case obvious. However, it does not explicitly mention alternatives or when not to use it, though the context is sufficiently distinct that exclusions would be redundant.

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