Prefeitura SP São Bernardo do Campo: Certidão Negativa de Débitos

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

Annotations show idempotentHint=true and destructiveHint=false, and description aligns: it mentions non-expiring connection, session-only login, and that calling with no args gives link. It doesn't contradict annotations, but adds minimal behavioral detail beyond what annotations already provide (e.g., no mention of side effects like browser redirects or timeout 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 a single, information-dense sentence that front-loads the main purpose and quickly explains usage options. It includes necessary details about token and link, but could be more concise by separating sentences; still, it earns its length.

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 (one optional param, no output schema), the description covers the essential context: how to authenticate, two methods, and the recommendation for persistent vs session. It is complete enough for an IDE agent to decide and invoke, though it could mention potential errors or prerequisite (browser login step is implied).

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 only one optional 'token' parameter with no description coverage (0%). The description explains the token's usage ('paste it here' or 'with no args'), which adds meaning beyond the schema's bare string type. However, it doesn't explain the token format (JWT mentioned in one phrase) or other potential parameters, so it partially compensates but not fully.

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: authenticating via login in browser and copying an access token. It specifies the tool accepts a token or returns a link, distinguishing it from sibling tools like 'connect' and 'show_version' which likely 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?

Provides explicit usage instructions: recommends adding token to config for permanent connection, or pasting token for session-only login. It explains when to use this tool (first-time auth) vs alternatives implicitly, but lacks explicit exclusions or when not to use.

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 clear. The description adds behavioral context about the two possible states (all connected vs. missing credentials) and what URLs are returned, which is useful but does not go beyond what annotations already cover in terms of side effects.

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 primary purpose, and every sentence adds value. It efficiently covers the main output and the edge case of missing credentials without redundancy.

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 has no parameters, no output schema, and simple annotations, the description is fairly complete. It explains the two states and the URLs returned, which is sufficient for an agent to understand the tool's behavior. However, it could mention whether the tool requires prior authentication or if it triggers any side effects, but annotations already cover safety.

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 provides no parameter semantics. The description compensates by explaining the output behavior in different states, which is the only relevant semantic information. With 0 params, baseline is 4, and the description meets that by clarifying the return values.

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, and distinguishes between all-connected and missing-credentials states. It is specific about the resource (connection status) and the output (authenticated flag, pending array, connect URLs), which differentiates it from siblings like authenticate and toolkit_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?

The description implies usage for checking connection status, but does not explicitly state when to use this tool versus alternatives like authenticate or toolkit_info. It provides context on what the tool returns in different states, but lacks explicit when-to-use or 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?

Beyond the annotations, the description discloses permission requirements ('Writes ... require workspace owner/admin'), the one-off execution behavior of invoke, the fact that invoke works even when the MCP is not installed, and the credential/payment link flows. No contradiction with 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 long but densely informative; every sentence adds meaningful guidance. It uses labels like 'KEY', 'Core flow', and 'Use install only' to create structure, though it could benefit from bullet points or short paragraphs for easier scanning.

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, and no output schema, the description is remarkably complete: it covers the core workflow, installation vs one-off invocation, auth and payment edge cases, permissions, billing actions, and the separate prompt library subsystem. It explains expected return artifacts for describe, invoke, get_prompt, and publish_prompt.

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 well by explaining the meaning of the action enum, tool_id selection via describe, and prompt_slug/publish_prompt flow. However, several parameters like limit, immediate, tier_slug, conversation, prompt_targets, request_details, and cancel_reason receive no explanation, so it is not fully sufficient.

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 the official mcp.ai marketplace covering both discovery and execution of MCPs/tools. It goes beyond a vague verb by explaining the core flow (search → describe → invoke) and distinguishes this router-style tool from its siblings by enumerating its many capabilities.

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?

Provides explicit guidance on when to use each action: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', and describes the retry flow for connect/checkout links. It also explains when subscribe/cancel, request_mcp, and prompt-library actions are 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds context about payment (prepaid credits), data source (official), and LGPD compliance, which is useful. However, it doesn't disclose what happens on failed queries, rate limits, or whether results are cached. The description doesn't contradict 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 a single paragraph, reasonably concise, and front-loaded with the core purpose. It includes necessary legal and payment context without excessive verbosity. However, it could be better structured with bullet points or clearer separation of purpose, usage, and compliance.

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 has 7 parameters, 5 required, no output schema, and no parameter descriptions, the description is insufficient. It doesn't explain the difference between 'cpf' and 'requerente_cpf', nor the 'inscricao' field. It also doesn't describe the return format or what a successful consultation looks like. The legal and payment context is helpful but doesn't compensate for the lack of operational detail.

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 mentions 'requerente' fields (CPF, nome, email, telefone) and 'inscricao' but doesn't explain their meaning or format. The schema has 7 parameters with no descriptions, and the tool description only vaguely references 'consulta' without detailing which parameters are needed for what. This is a significant gap for a tool with 5 required 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 the tool's purpose: consulting Certidão Negativa de Débitos (negative debt certificate) from São Bernardo do Campo's official source. It specifies the resource (CND) and the action (consultar), and distinguishes it from generic tools by naming the specific municipality and certificate type. However, it doesn't explicitly differentiate from sibling tools, though siblings are unrelated (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 implies usage context: it's for consulting official Brazilian sources, requires prepaid credits, and is hosted by the platform. It mentions the client is the data controller under LGPD, which hints at compliance requirements. However, it doesn't explicitly state when to use this tool vs alternatives, nor does it mention any exclusions or prerequisites beyond payment.

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 implies a write operation ('Report') with no annotation contradiction; annotations show readOnlyHint=false and destructiveHint=false. However, it does not state what happens after submission (acknowledgment, response format, rejection cases) or whether the report is reversible, which matters for a tool with no output schema.

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 concise sentences with the primary purpose front-loaded. The second sentence provides actionable guidance (include conversation array). No filler words, but it could be merged into one sentence without loss. Still appropriately compact.

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 3 parameters at 0% schema coverage and no output schema, the description partially compensates by naming 'conversation array' and 'reproduction.' However, it doesn't explain the 'context' parameter, what happens after reporting (response/confirmation), or whether this is a fire-and-forget call. For a reporting tool with no annotations covering mutation behavior, more context would be helpful.

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 partially does: it explains the 'conversation' parameter should contain recent messages for reproduction bugs Dev. However, it does not explain the 'context' parameter at all, and it doesn't clarify that 'conversation' is a JSON array string (though it implies it). The description adds some value beyond the schema but leaves context undocumented.

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: 'Report a bug, missing feature, or send feedback.' It uses a specific verb ('report') and enumerates the scope of acceptable messages (bug, missing feature, feedback), which distinguishes it from the sibling tools (authenticate, toolkit_info, 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 the 'how' (include conversation array) but no 'when to use' guidance relative to sibling tools. It doesn't state prerequisites, conditions triggering its use, or what distinguishes it from similar reporting paths (e.g., feedback via marketplace). The actionable instruction is limited to including the conversation for reproduction.

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, idempotent, non-destructive, and openWorldHint false. The description adds that it shows both platform and adapter versions, which is useful. There is no contradiction. Since the tool is simple and side-effect free, the description covers the key behavior adequately.

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 is front-loaded with the verb 'Show' and the resource. It is immediately clear and contains no fluff. It earns its place.

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 zero parameters concerns and strong annotations (read-only, idempotent), the description is complete enough. It does not explain return format, but with no output schema and a simple version query, that is acceptable. It could be slightly improved by indicating what 'versions' includes (e.g., exact numbers), but the current level 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 schema has zero parameters)Skip; the description correctly mentions no parameters. With no parameters, the baseline is 4 because there is nothing to explain. The description does not add anything about parameters, but that is appropriate.

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: showing the current MCP platform and adapter versions. It uses a specific verb and resource, and is unambiguous. It is distinct from siblings that handle 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 clearly implies a usage context: when you need to check the versions of the platform and adapter. There are no explicit when-not-to-use or alternative tool mentions, but the tool is simple enough that guidance is minimal. However, it lacks explicit context on when to use this versus toolkit_info, which may also provide version info.

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, and the description does not contradict them. The description adds value beyond annotations by specifying what state is returned (installed MCPs, connection status, accounts, catalog counts), which gives the agent a concrete picture of the response.

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 with a front-loaded main clause and a colon-separated list of the exact data categories returned. Every word adds information, and there is no fluff or redundancy.

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 state inspection tool, the description is complete: it names the resource and the four specific categories of information returned. It does not need to explain return values in more detail because the described content is the return value, and there are no input parameters or complex side effects to cover.

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% (empty object), so there are no parameter semantics to explain. The baseline of 4 applies because the description correctly does not invent parameter information and the schema/empty parameter set fully covers this dimension.

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 ('current toolkit state') and itemizes exactly what that includes: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from siblings like 'show_version' or 'authenticate', which are about different concerns.

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 when an agent needs an overview of the toolkit's installed integrations and their health, but it does not explicitly say when to prefer this over alternatives or when not to use it. The context is clear enough to infer intended usage, but explicit guidance is missing.

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