Prefeitura PE Recife: NFS-e (Nota Fiscal Eletrônica de Serviços)

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

The description explains behavioral details beyond the annotations: the login happens in the browser, the config-header path is permanent/non-expiring, and pasting a token is session-only. It does not contradict annotations (idempotentHint is reasonable for login attempts), though it omits error/expiry behavior.

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 appropriately sized for a one-parameter auth tool and front-loads the browser-login concept. It is slightly run-on with multiple instructions in one flow, but every sentence conveys necessary 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 simple auth tool with no output schema, the description covers the key usage paths (config header, token paste, no args), the return behavior (get the link), and the permanent-vs-session distinction. It does not detail failure cases or what the successful token response looks like, but the constraints are modest.

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 only shows an optional 'token' string with no description (0% coverage), so the description carries the full burden. It explicitly says the token is a JWT pasted by the user, that it is optional, and that omitting it returns 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 as an authentication flow: the user logs in in the browser, copies an access token, and the tool accepts it or returns a login link. It distinguishes this from general connection/configuration actions, though it does not explicitly contrast with the sibling 'connect' tool.

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 instructions for two modes: permanent configuration via an Authorization header, and session-only login by passing a token. It also states exactly when to call with no args (to get the link) and when to call with a token (after the user pastes 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, idempotentHint, and destructiveHint false. The description adds value by explaining the conditional return structure (authenticated:true with empty pending[] vs connect_url for missing credentials), which is not captured in 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 two sentences, concise, and front-loaded with the core action ('Returns connection status and URLs'). It efficiently communicates the key outcomes without padding.

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 status tool with no output schema, the description reasonably covers the primary states (all connected vs missing credentials) and mentions the return fields (authenticated, pending[], connect_url). It could be more exhaustive about edge cases, but it is sufficient for the tool's 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?

The tool has zero parameters, so the schema is trivially complete. Per the rubric, a baseline of 4 is appropriate when there are no parameters, and the description correctly avoids adding unnecessary parameter details.

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 connection status and URLs, with specific conditions for authenticated vs missing credentials. This distinguishes it as a read-only status check, though it doesn't explicitly contrast with sibling tools like '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 implies usage for checking connection status but does not explicitly state when to use this tool instead of alternatives like 'authenticate' or 'show_version'. The conditional outputs provide context about behavior, but no direct guidance on when to invoke 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?

The description discloses many behaviors not in annotations: invoke works without install, returns connect/checkout links, requires auth for writes, and distinguishes installed_in_toolkit vs workspace. These significantly enrich the agent's understanding beyond the minimal annotations (readOnlyHint=false, openWorldHint=true).

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?

While long, the description is logically structured: it opens with the tool's essence, then explains the search→describe→invoke flow, key behaviors, installation distinctions, and the separate prompt library. It is front-loaded and each section adds value, though it could be tightened for readability.

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 parameters, many actions), the description is remarkably complete: it covers discovery, execution, installation, auth, payment, writes, and the prompt library. It also hints at return values (e.g., 'describe returns full profile', 'invoke returns connect/checkout links'), making it sufficient for an agent to use correctly without an output schema.

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 explains key parameters like action, mcp_id, tool_id, arguments, and prompt-related fields through the core flows, but does not systematically define all 23 parameters (e.g., tier_slug, cancel_reason, prompt_targets). It covers enough to guide correct usage but leaves some 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 it is the official mcp.ai marketplace catalog and execution interface, with a specific verb 'search', 'describe', 'invoke', etc. It distinguishes from siblings by being the central hub for tool discovery and execution, while also covering the prompt library separately.

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 explicit guidance on when to use invoke vs install (e.g., 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'), and mentions alternatives like report_bug and request_mcp. It also clarifies that writes require owner/admin, helping the agent decide when to act.

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 known. The description adds important context: it's hosted by the platform, requires prepaid credit, and the client is data controller (LGPD). This goes beyond annotations and helps the agent understand external constraints.

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 paragraph that is front-loaded with the tool's purpose. It includes several relevant caveats (no credentials, prepaid credit, LGPD). It is reasonably concise given the amount of regulatory context it conveys, though it could be slightly more 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?

The tool has 4 parameters, no output schema, and low schema description coverage. The description lacks detail on how to construct the query (e.g., whether cpf or cnpj is needed, what the returned data looks like, potential errors). Given the moderate complexity, the description is not fully complete for an agent to use it without additional exploration.

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 parameter meaning. The description does not explain any parameter roles beyond the schema's property names. It mentions 'numero_nota' and 'codigo_verificacao' implicitly in the description but does not explain how those are used, nor the optional cpf/cnpj. Since coverage is 0% and the description adds nothing about parameters, the score is low.

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 NFS-e (electronic service invoice) data from the official Recife, PE source. It specifies the resource (NFS-e) and the action (consulta). It distinguishes from siblings (none are similar since siblings are generic platform tools like authenticate or report_bug).

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 the context: it uses official sources, is available to citizens, requires prepaid credits, and does not require platform credentials. It does not explicitly say when to use this tool vs alternatives, but given the siblings are unrelated, the context is clear. It also implies compliance responsibilities.

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, destructiveHint=false, and idempotentHint=true, so no contradiction exists. The description adds useful context by instructing to 'Include the conversation array with recent messages for reproduction,' which aids behavioral understanding. However, it does not elaborate on side effects, error handling, or rate limits. The added context is minimal but non-trivial, so a baseline 3 is warranted.

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 consists of two sentences, with the purpose front-loaded. Every word earns its place, and the additional instruction about the conversation array adds value without redundancy. It is highly 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 relatively simple, non-complex tool with 3 parameters and no output schema, the description provides a basic but adequate purpose. However, the lack of parameter guidance (especially for 'message') leaves gaps for an agent to invoke it correctly. The tool is not overly complex, so a 3 reflects that it is minimally viable but not comprehensive.

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 by explaining parameters. It only mentions 'conversation array' but does not clarify the format or meaning of 'context' or 'message.' The required 'message' parameter is completely undocumented in the description. This fails to compensate for the lack of schema descriptions, warranting a low 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 states the tool's purpose: 'Report a bug, missing feature, or send feedback.' This uses a specific verb and resource, distinguishing it from sibling tools like 'marketplace' or 'show_version.' It unambiguously identifies when an agent should use this tool.

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 when to use the tool ('Report a bug, missing feature, or send feedback') without explicitly excluding alternative tools. While no alternatives are named, the context given is clear and sufficient given the sibling tools are unrelated. A score of 4 is appropriate as there is clear usage context, though no explicit 'when not to use' 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that it returns version information, but goes beyond the annotations by specifying that it shows both platform and adapter versions. However, it doesn't disclose additional behavioral traits such as whether it contacts external services (openWorldHint is false, but the description doesn't clarify) or the exact format of the output. With annotations providing the core safety hints, this is acceptable but could add a bit more 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 sentence, highly efficient, and front-loaded with the verb and resource. It contains no unnecessary words or repetition. Every part of the sentence adds value, making it a model 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?

Given the tool's simplicity (no parameters, no output schema, clear annotations), the description provides adequate context. It tells the agent what the tool does without missing critical information. The only minor gap is that it doesn't mention how the version information might be used or whether it requires any prior authentication (though 'authenticate' is a sibling tool, suggesting it might be needed). However, given the simplicity, the description is nearly 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 tool has zero parameters, and the schema is empty. The description adds meaning by clarifying that the tool displays version information without requiring any input. Since there are no parameters to explain, the description compensates by clearly indicating what the tool does with no inputs, which is sufficient for the agent to know call expectations.

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: 'Show the current MCP platform and adapter versions.' It uses a specific verb ('Show') and a specific resource ('current MCP platform and adapter versions'), which effectively differentiates it from sibling tools like authenticate, connect, or marketplace. Its function is obvious even without the title.

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 that this tool is used to check version information, which is appropriate when an agent might need to verify the environment or report an issue. However, it does not explicitly state when to use this tool versus others, nor does it provide exclusions or alternatives. Given its simplicity and clear scope, the implied context might be sufficient, but it lacks explicit 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds context about returned information but doesn't disclose any additional behavior like data freshness, potential delays, or whether it summarizes across multiple MCPs. Given annotations provide the key safety information, this is adequate but not rich.

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 packs all key elements: what it returns (toolkit state), the specifics (installed MCPs, connection status, accounts, catalog tool counts). There's zero fluff; it is front-loaded with the most important verb 'Returns' and resource 'current toolkit state'.

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 info tool with no parameters and no output schema, the description is complete enough. It covers the main deliverables (installed MCPs, connection status, accounts, catalog tool counts). A brief mention of the purpose (e.g., 'Use to diagnose connectivity') would make it even more complete, but for a low-complexity tool, this is adequate.

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 are no parameter semantics to document. The description doesn't need to add parameter meaning. With schema coverage at 100% (vacuous for zero params), the description appropriately focuses on what the tool returns rather than parameters.

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 what the tool does: returns the current toolkit state—installed MCPs, connection status, accounts connected, and catalog tool counts. It mentions specific resource (toolkit) and the information returned. While it doesn't explicitly differentiate from siblings, the scope is distinct enough (state inspection vs. authentication, connection, 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 implies usage for checking toolkit status but doesn't explicitly state when to use it vs. alternatives. It doesn't mention that it's a read-only diagnostic or that it should be used before other actions. Sibling tools like 'connect' or 'authenticate' could be alternatives, but no exclusion guidance is provided.

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