Prefeitura SC Florianópolis: Certidão Negativa de Débitos

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

Annotations already indicate idempotentHint: true, and the description additionally discloses that calling with no args returns a browser link, that the token is a JWT for session-only login, and that the recommended config approach works for a permanent non-expiring connection. It also notes the process (user pastes token). This provides rich behavioral context 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 is concise and front-loaded with the purpose, then provides key usage details in three sentences. Every sentence earns its place: purpose, permanent method, session method. 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?

Given the tool is a simple authentication with one optional parameter, no output schema, but annotations provide idempotency and non-destructive hints, the description fully covers the needed context: how to initiate login, permanent vs. session options, and expected input. The complexity is low and the description addresses all critical aspects.

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 has one optional parameter 'token' with no description, so schema coverage is 0%. The description compensates by explaining that token should be passed after user pastes it, provides the format { token: "<jwt>" }, and clarifies that no args yields the link. It doesn't detail token format beyond JWT, but for a single optional param this is adequate.

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: it authenticates the agent with MCP.AI by either providing a login link or accepting a token for session-only login. It also actively points to a better alternative (adding Authorization header to config) for permanent access. This distinguishes it from sibling tools like marketplace or toolkit_info, as it's specifically the authentication entry point.

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 guidance: it suggests the preferred method (config header) and when to use the session token, and explains the no-args behavior (get link). It even contrasts with the alternative of permanent configuration, providing clear decision-making context for the agent.

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 and idempotentHint, which cover safety. The description adds behavioral context beyond annotations by specifying conditional return values (authenticated:true vs connect_url and per-install URLs). This enriches the agent's understanding without contradicting any 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 exactly two sentences, front-loads the primary purpose, and uses no redundant wording. Each clause delivers the necessary information about both output states, making it highly efficient.

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 that the tool takes no parameters, the description fully covers the behavior for both connection states (connected and missing credentials). There is no output schema, but the description provides sufficient detail on return values. It is complete for a status-checking 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?

The tool has zero parameters and the schema is empty (100% coverage). No parameter documentation is needed, so the description adds no parameter info. Per the rules, a zero-parameter tool gets a baseline of 4, and the description does not need to compensate for any gaps.

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.' It specifies the resource (connection status) and the action (returns), and the conditional behavior differentiates it from sibling tools like authenticate and toolkit_info, which handle other aspects.

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 implicit guidance by explaining two distinct output scenarios: when all providers are connected and when credentials are missing. This helps an agent infer that the tool is for checking status rather than performing authentication. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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 key behaviors beyond annotations: invoke runs a one-off even if not installed, returns connect/checkout links for auth/payment and then retry, install makes permanent, and writes require owner/admin. This adds crucial context about side effects, permissions, and auth flows that annotations don't cover.

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 covering a complex tool with 14 actions and a prompt library. While lengthy, every sentence adds value without redundancy. However, it could be better structured (e.g., bullets) for readability, and the length is borderline for being considered concise.

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, no output schema, minimal annotations), the description is impressively complete. It covers all actions, edge cases (not installed, auth, payment, permissions), and even the prompt library, making it sufficient for an agent to use the tool effectively without additional documentation.

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 carries the full burden. It explains the action enum and the purpose of each major parameter (action, mcp_id, tool_id, arguments, etc.) through the core flow and specific behaviors (e.g., invoke needs tool_id). It also covers prompt-related parameters implicitly via get_prompt and publish_prompt mentions.

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 the official marketplace for MCPs and tools, covering discovery, usage, and management. It explicitly lists the core flow (search → describe → invoke/install) and distinguishes from sibling tools by focusing on catalog and execution. It also mentions the prompt library, making the scope very specific.

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 explicit guidance on when to use each action, such as 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT in the active toolkit'. It also contrasts with list_tools for callable tools and mentions request_mcp for new builds, giving clear alternatives and context.

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, so the safety profile is clear. The description adds context: hosted by the platform, no platform credentials needed, paid per consultation with prepaid credit, and LGPD compliance note. It doesn't describe what the response looks like or potential errors, but given annotations, this is acceptable.

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 paragraph, concise and front-loaded with the tool's purpose. It contains useful context about payment and LGPD. No wasted words, but 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 moderate complexity (4 optional parameters, no output schema). The description covers purpose, payment, and data responsibility, but lacks parameter guidance and output expectations. Given the annotations cover safety, the description is adequate but not complete. It doesn't explain which parameter to use for what entity (CPF vs CNPJ) or if any is required.

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 parameters at all. It lists the names in the schema (cpf, cnpj, nome, codigo_contribuinte) but the description doesn't clarify their meaning, required format, or which combinations are expected. The description mentions consultation but doesn't link to the parameters. With 4 parameters and no schema description, the description should have explained 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 provides a 'Certidão Negativa de Débitos' (negative debt certificate) consultation from the official Florianópolis city government source. It specifies the resource (tax certificate) and the action (consult). It doesn't explicitly differentiate from siblings, but the sibling tools are general system tools (authenticate, connect, etc.), so the purpose is clear enough.

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: consult official Brazilian source for debt certificates. It mentions payment via prepaid credits and that data is not confidential. However, it doesn't explicitly state when to use vs. not use, or mention alternatives. There is no guidance on which parameters to provide (e.g., CPF vs CNPJ).

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 are present: readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds context about including conversation for reproduction, which is beyond schema. It does not contradict annotations. It does not disclose any side effects or errors, but given the annotations, it is minimally sufficient.

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, which is concise. It front-loads the purpose and then gives a hint about payload. No wasted words, but it could be slightly more structured with explicit parameter 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?

The tool is relatively simple (3 params, no output schema, no nested objects), but with zero schema coverage, the description must explain all parameters and behavior. It only hints at 'conversation' and leaves 'message' and 'context' under-specified. Also, no mention of response or when to use each field. Incomplete for a tool with zero schema description coverage.

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 carries the burden. The description mentions the 'conversation' array and 'recent messages' for reproduction, which gives some meaning to the 'conversation' parameter, but it does not explain 'message' or 'context' beyond what the schema shows (type/required). The 'context' parameter is not explained at all. With zero coverage, the description fails to compensate for most 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 states the tool reports bugs, missing features, or feedback, which is clear and specific about the resource and action. It does not explicitly differentiate from siblings, but sibling names like 'authenticate', 'connect', 'marketplace' suggest a broader suite, and the purpose is clear enough.

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 the tool (to report issues) but does not provide explicit when-not-to-use guidance or alternatives. Given the sibling list, there is no obvious alternative for bug reporting, but the instruction to include conversation array is a usage hint. Still, it lacks explicit exclusions.

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 the specific behavioral detail that it reports both 'MCP platform and adapter versions', which goes beyond the generic annotations and provides useful context about what exactly is shown.

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, concise sentence that immediately conveys the tool's purpose. No unnecessary words or fluff. Every word earns its place, and the key information is 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 parameterless, read-only version tool with no output schema, the description is complete. It tells the agent exactly what the tool does. There is no additional context needed such as authentication or error handling details given the trivial nature of the operation. The simplicity is appropriate for the tool's 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?

The tool has zero parameters, and the schema description coverage is 100%. Per the rubric, the baseline is 4 for zero parameters. The description does not need to add parameter details since none exist, and there is no 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 'Show the current MCP platform and adapter versions' uses a specific verb 'show' and clearly identifies the resources 'MCP platform and adapter versions.' It is unambiguous and distinguishes this tool from siblings like 'authenticate' or 'connect' which have entirely 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 implies when to use the tool (when you need version information) but does not explicitly state alternatives or exclusions. There is no mention of when not to use it or mention of sibling tools like 'toolkit_info' that might also provide version details. This is implied usage at best.

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 and idempotentHint, and the description adds concrete details about what the return includes, going beyond the safety profile. It does not disclose potential costs or latency, but for a simple info tool, the added context is sufficient.

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 sentence that efficiently communicates the tool's purpose and scope without redundancy. Every clause adds value.

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 parameters and no output schema, the description fully specifies what the agent can expect from the tool. It provides all necessary context for safe invocation and interpretation.

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 baseline of 4 applies. The description appropriately avoids irrelevant parameter details, and there is nothing to document beyond the returns.

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 the toolkit state, enumerating specific elements (installed MCPs, connection status, accounts, catalog tool counts). It is distinct from siblings like authenticate or connect, making the purpose 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 usage for inspecting current toolkit state but does not explicitly state when to use it versus alternatives. Given its read-only informational nature, the context is clear enough, but it lacks explicit exclusions or timing guidance.

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