Prefeitura SP Osasco: Certidão Tributária de IPTU

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

Annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) align with the description. The description clarifies the two connection types (permanent vs session) and implies idempotency by allowing repeated calls with same token. It also notes the link generation.

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 but skillfully organized with a colon to separate purpose from instructions. It's slightly long but remains focused and scannable.

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?

Covers both permanent and session authentication paths, explains the no-args behavior. It doesn't describe the return value for the token case, but given the tool's simplicity, this is acceptable. No contradictions with annotations.

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 provides no description for the token parameter (coverage 0%), but the description explains it as the access token to be pasted. It also clarifies the parameter is optional (no args to get link), which the schema doesn't indicate since it's not required. This compensates well.

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 'authenticate' for IDE agents, with the purpose of obtaining and using an access token for login. It distinguishes between permanent config-based auth and session-based token auth.

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 step-by-step instructions: log in in the browser, copy token, either configure as header or pass as parameter. It explicitly explains the two invocation modes: with token or without to get the link, which is actionable for an 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=true, destructiveHint=false, and idempotentHint=true. The description adds valuable behavioral context by specifying the exact response structure under different conditions (authenticated:true with empty pending[], or connect_url and per-install URLs). This goes beyond the annotations and helps the agent predict behavior. However, it does not mention all possible edge cases (e.g., partial connectivity), but for a read-only status tool, it is thorough.

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

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

The description is two sentences, front-loaded with the core purpose, and efficiently explains conditional outcomes without fluff. Every word adds value, and the structure is easy to parse.

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 read-only status tool with no parameters and no output schema, the description is complete. It covers both connected and missing-credential scenarios, which are the primary use cases. The presence of sibling tools like 'authenticate' and 'connect' clarifies its role without needing extensive extra context.

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 all needed semantics by default. According to the rubric, 0 params results in a baseline of 4. The description appropriately avoids inventing parameter details and focuses on its output behavior.

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 'Returns connection status and URLs', using a specific verb and resource. It differentiates from siblings like 'authenticate' by focusing on status checking rather than initiating auth. The scope is well-defined with conditional behaviors based on connection state.

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 by describing conditional outcomes ('When all providers are connected', 'When credentials are missing'), giving context for when to expect different results. However, it does not explicitly state when to use this tool over alternatives or mention any exclusions. The guidance is implied rather than explicit, so it does not fully meet the 'clear context' threshold of a 4.

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 only provide generic hints (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds substantial operating context: invoke runs one-off even when the MCP is not installed, auth returns a connect link, unpaid returns a checkout link, writes require owner/admin, and search/describe flag installation state. 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 dense but front-loaded, starting with identity and the core flow before covering edge behaviors, permissions, and the prompt library. Every sentence carries distinct operational value, and the length is justified by the tool's 14 actions and dual marketplace/prompt-library scope.

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 complex action-dispatcher with 23 parameters and no output schema, the description covers the operating model, the one-off vs permanent distinction, auth/payment outcomes, permission requirements, and the separate prompt library. This is sufficient for an agent to select actions and anticipate key behaviors.

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 and 23 parameters, the description carries a heavy burden. It explains the key action-driven parameters (action, tool_id, arguments, prompt_body, prompt_slug, prompt_vars) and the overall dispatch model. However, several parameters (limit, immediate, tier_slug, cancel_reason, prompt_targets, request_details, etc.) are left to inference rather than explicitly explained.

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 this as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It names concrete capability requests it serves and explicitly distinguishes itself from sibling tools by positioning itself as the marketplace/search/invoke dispatcher.

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 an explicit core flow (search → describe → invoke), contrasts 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT', and routes to list_tools, subscribe/cancel, report_bug, and request_mcp. This provides strong when-to-use and 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. The description adds meaningful behavioral context beyond those: it is a paid consultation (prepaid credit), does not require platform credentials, accesses non-confidential official data, and places LGPD responsibility on the client. This goes beyond the annotations and provides useful operational details.

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 (4 sentences), front-loaded with the main purpose, and each sentence adds distinct information: purpose, payment model, data source, and legal compliance. No redundant content, though the flow 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?

With 4 required parameters, no parameter descriptions, no output schema, and no explanation of expected inputs or return values, the description is not complete enough to guide an agent in correct invocation. It covers the 'why' and legal aspects but leaves out the 'how' (parameter meanings) and 'what to expect' (output format).

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 4 required parameters with no descriptions (0% schema coverage), and the description does not explain what 'cdc', 'finalidade', 'cpf_solicitante', or 'telefone_solicitante' mean. The only indirect hint is the LGPD mention of 'finalidade legítima', which may relate to the 'finalidade' parameter, but this is insufficient for correctly populating the required fields.

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: 'Certidão Tributária de IPTU, consulta em fonte oficial' (IPTU Tax Certificate consultation from an official source). It uses a specific verb (consulta) and names the resource, distinguishing it from the generic sibling tools (authenticate, connect, 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 context on how the tool is used: hosted by the platform, no platform credentials needed, prepaid credit payment, and it accesses official Brazilian sources. However, it does not explicitly state when to use this tool over alternatives or mention any exclusions. The siblings are unrelated, so the lack of alternatives is less critical, but the usage context is implied rather than explicit.

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=false (write), idempotentHint=true (repeatable), and destructiveHint=false (non-destructive). The description adds context about including the conversation array for reproduction, which is beyond the annotations. However, it does not disclose what happens after reporting (e.g., ticket creation, response timing) or any side effects. With annotations covering the safety profile, this is a minimally adequate score.

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 purpose, and the second sentence provides a key usage detail. There is no redundant information or filler. Every word adds value, making it highly concise and well-structured.

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

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

For a simple tool with 3 parameters, no output schema, and modest annotations, the description is adequate but incomplete. It clearly states the purpose and hints at usage (including the conversation array), but lacks explicit parameter guidance and doesn't describe the tool's context relative to the system beyond the immediate purpose. Given its simplicity, a 3 is appropriate—it meets the minimum viable standard without being exhaustive.

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 0% description coverage, so the description must compensate. It partially explains the 'conversation' parameter ('Include the conversation array with recent messages for reproduction') but provides no meaning for 'message' (the required parameter) or 'context'. Since only one of three parameters gets semantic explanation, and the description doesn't clarify the structure or purpose of the others, the parameter semantics are weak.

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.' It uses a specific verb ('report'/'send') and resource (bug/feature/feedback), and distinguishes itself from sibling tools which are for authentication, connection, marketplace, etc. The mention of including the conversation array adds scoping.

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 encounter a bug or want to give feedback) but does not provide explicit guidance on when not to use it or mention alternatives. It lacks a clear context for usage beyond the purpose, such as prerequisites or typical scenarios. Given the clear purpose, it is adequate but with gaps.

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

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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds useful context by specifying exactly what the tool reports—platform and adapter versions—which complements the annotations without contradicting them. It does not describe return format, but that is a minor gap for such a simple read-only operation.

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, front-loaded sentence with no filler. Every word earns its place, and it conveys the complete tool purpose 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?

For a zero-parameter, read-only version-inspection tool with strong annotations, the description is sufficiently complete. It clearly states what the tool does. A slightly richer description could mention the expected return shape, such as a version object with separate fields, but this is not essential for the tool's simple use case.

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 is 4. The description adds semantic value by explaining what version information is shown, fully compensating for the absence of 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 states the verb 'Show' and the resource 'current MCP platform and adapter versions,' making the tool's purpose immediately understandable. It is specific enough to distinguish from auth, connection, and data-query siblings, though it does not explicitly differentiate from toolkit_info, which could potentially overlap in scope.

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 context is clear: use this tool when you need to know the current MCP platform and adapter version numbers. It does not explicitly mention when not to use it or alternatives like toolkit_info, but for a zero-parameter info tool, the usage scenario is obvious and self-contained.

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 transparency about the exact contents of the returned state (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotations. It does not describe potential behavior like network delays or format specifics, but it is effective for a zero-parameter read-only tool.

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 immediately states the function ('Returns the current toolkit state') and then itemizes the key contents. Every phrase adds information, with no filler or repetition of schema details. It is an exemplary 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?

For a tool with no parameters and no output schema, the description provides complete context: it enumerates all the categories of information the tool returns and implies the state is comprehensive. Given the annotations cover side-effect safety and the sibling set includes many action tools, this description is fully adequate for an agent to decide when to use it and 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?

The tool has zero parameters, and the schema correctly reflects that with no properties. Per the rubric, the baseline for 0 params is 4, and the description does not need to compensate for any missing parameter documentation. It correctly focuses on the output rather than inputs.

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 the specific verb 'Returns' with a clear resource ('current toolkit state') and enumerates the exact information provided (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools like authenticate or connect, which perform actions, and show_version, which likely returns a single version string.

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 its use as an informational snapshot of the toolkit's health and configuration, which is distinct from the action-oriented siblings. However, it does not explicitly state when to use it instead of another tool (e.g., 'to check connectivity, use this tool'), so it falls short of the explicit when/when-not guidance that would earn a 5.

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