Prefeitura SP São Paulo: Segunda via Simplificada de IPTU

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

The description discloses behavioral aspects beyond annotations: calling with no args yields a login link, while providing a token enables a session-only login. It also explains permanence differences between config-based and session-based methods. This adds useful context beyond the annotations (idempotentHint true, destructiveHint false) without contradiction.

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 compact yet dense with information, using three sentences to convey purpose, two usage modes, and parameter behavior. It front-loads the purpose and avoids fluff, though it is slightly more verbose than strictly necessary.

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 (auth flow with two modes), the description covers all essential aspects: how to obtain access, token vs config, session vs permanent, and how to invoke. No output schema exists, but the description doesn't need to explain return values. Minor omissions like error handling or post-auth behavior, but overall sufficient for an auth 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 only parameter 'token' is undocumented in the schema (0% coverage), but the description fully explains its meaning: a JWT for session-only login, and that omitting it returns a link. This fully compensates for the schema gap, making the parameter's purpose and usage unambiguous.

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: authenticating the MCP.AI server for IDE agents by logging in, obtaining an access token, and supporting two modes (permanent via config header vs session-only via token). It distinguishes itself from sibling tools by focusing specifically on authentication, not general connectivity or utilities.

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 usage scenarios: 'Best: add it to this server's config as a header...' for permanent access, and 'Or paste it here for a session-only login' with clear instructions to call with a token or without args. It does not explicitly mention when not to use this tool or contrast with 'connect', but the context is clear enough for an IDE agent to decide 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 adds significant behavioral context beyond the readOnlyHint and idempotentHint annotations by specifying exact response scenarios: returning authenticated:true when all providers are connected, and connect_url when credentials are missing. This enriches the agent's understanding of runtime 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 two-sentence description is concise, front-loads the main purpose, and uses a clear conditional structure to explain response variations. Every word 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?

For a stateless, zero-parameter status tool, the description fully covers the relevant outcomes and the meaning of the response fields. Combined with the safe annotations, no additional context seems missing.

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 zero parameters, the baseline is 4. The description does not need to add parameter details, and the schema coverage is trivially 100%. No further explanation is necessary.

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,' using a specific verb and resource. It distinguishes itself from siblings like 'authenticate' by focusing on status retrieval, and the conditional behavior further clarifies its purpose.

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 this is the tool to check connection status, but it does not explicitly state when to use it over alternatives or provide exclusions. The usage context is implied rather than explicitly guided.

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 critical behaviors beyond annotations: invoke runs one-off without installing, returns connect/checkout links when needed, permissions required for writes, and how search/describe flag installation status. It aligns with annotations and adds substantial contextual detail.

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, but front-loaded with the core purpose and well-organized around the flow. It is longer than ideal but every sentence contributes value; minor improvement would be bullet points for clarity, but it remains 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 the tool's high complexity (14 actions, 23 params, prompt library, payment/auth flows) and no output schema, the description covers the vast majority of behaviors and use cases, including permissions and edge conditions. Missing parameter semantics slightly reduce completeness.

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, and it explains the action enum and key parameters (mcp_id, tool_id, arguments, prompt fields) through the described flow. However, it does not explain all 23 parameters (e.g., limit, query, conversation, immediate, tier_slug) explicitly, leaving 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 identifies the tool as the official mcp.ai marketplace, explaining both its catalog role and its execution capability. It distinguishes itself from sibling tools by covering all marketplace actions and the prompt library, with a specific verb (marketplace) and resource (MCPs/tools).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance for each action (search, describe, invoke, install, list_tools, subscribe, etc.), including when to prefer invoke over install and how to handle credentials/payment. It also contrasts with other tools implicitly by covering the entire marketplace workflow.

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 that the tool requires per-query payment via prepaid credits, that no platform credentials are needed, that the data is not confidential, and that the client is the LGPD controller. This expands beyond the annotations without contradicting them.

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

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

The description is moderately concise but contains redundant statements about official sources ('fonte oficial' and 'fontes e órgãos oficiais brasileiros') and includes LGPD boilerplate that may not be necessary for tool selection. It could be streamlined without losing essential 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?

Despite the clear purpose, the tool lacks an output schema and the description does not explain what the query returns (e.g., the actual second copy details), nor does it clarify the meaning and usage of the four parameters. This leaves significant gaps for an agent trying to construct a valid request.

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 four parameters with zero description coverage, and the tool description does not explain any of them. In particular, 'sql' is ambiguous and could be mistaken for a structured query language string. Since the description fails to compensate for the 0% schema coverage, the agent is left without guidance on required meaning and format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a query for Simplified IPTU Second Copy from São Paulo, using the verb 'consultar' and specifying the official source. This distinguishes it from platform-level sibling tools like authenticate or connect, making its 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 provides context on how to use the tool (requires prepaid credits, no platform credentials) and clarifies it queries official public data, but it does not explicitly state 'use this when...' or contrast with alternative IPTU tools. However, since no domain siblings exist, the implied usage is sufficient.

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, providing a basic safety profile. The description adds that the conversation array is used for reproduction, which implies data transmission for debugging. However, it does not elaborate on potential side effects, data handling, or external communication, though the bar is lower given existing 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 exceptionally concise—two sentences total. It front-loads the purpose and then provides a direct, actionable instruction. Every word earns its place with 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 simple feedback tool with no output schema and minimal side-effect concerns, the description is reasonably complete. It explains the core purpose, guides on key parameter usage, and works well with the existing annotations. Minor gaps remain on the 'context' parameter and what happens after submission, but these are not critical for basic functionality.

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 does clarify that 'conversation' should contain recent messages for reproduction, which adds meaning to that parameter. However, 'message' and 'context' are left to rely on their names, and the format of the conversation array is not specified. Partial coverage of the 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: 'Report a bug, missing feature, or send feedback.' The verb 'report' and the resource (bugs/missing features/feedback) are explicit. It distinguishes itself from sibling tools like 'authenticate' or 'marketplace' by its unique function.

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 instructing to 'Include the conversation array with recent messages for reproduction,' which gives necessary context for effective use. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. It provides some usage guidelines but lacks explicit comparative 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 description need not repeat that. The description's verb 'Show' is consistent with these annotations, and it adds the specific resource (MCP platform and adapter versions), which is appropriate. No contradiction, and it doesn't need to disclose more for such a simple 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?

Single concise sentence that fully conveys the action and scope. No extraneous information, and it is front-loaded with the key 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 zero-parameter, read-only version display tool with clear annotations, the description is complete. It states exactly what versions it shows. No output schema is needed. The description is sufficient for an agent to know when to call 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?

Tool has 0 parameters, so the baseline is 4. The description doesn't need to explain parameters, and the schema has no properties, so there's nothing to elaborate on.

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 shows the current MCP platform and adapter versions. It is a specific verb ('Show') with a clear resource ('MCP platform and adapter versions'), and it is distinct from sibling tools like connect or marketplace.

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 (when you need version info) but does not explicitly contrast with alternatives or provide context on when to use this tool. Since there are no obvious alternatives among siblings, the usage is fairly obvious, but the description 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, establishing a safe read-only profile. The description adds valuable context beyond annotations by specifying exactly what is returned (installed MCPs, connection status, accounts, catalog tool counts), which fully discloses the tool's behavior without contradictions.

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 lists all key output facets without any fluff or repetition. It is front-loaded with 'Returns the current toolkit state' and immediately enumerates the details. Every part of the sentence 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?

Given the tool has no parameters, no output schema, and simple read-only behavior, the description is complete. It enumerates all relevant output categories (installed MCPs, connection status, accounts, catalog tool counts), giving the agent a clear understanding of what to expect. The sibling context does not introduce additional requirements.

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 fully documented (100% coverage). No parameter descriptions are needed. The description focuses on the output, which is entirely sufficient. Baseline of 4 for zero parameters is appropriate because there is no parameter complexity to explain.

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 current toolkit state with specific details: installed MCPs, connection status, connected accounts, and catalog tool counts. It uses a specific verb ('Returns') and resource ('toolkit state') and distinguishes itself from sibling tools like 'connect' or 'authenticate' by focusing on state inspection rather than actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates when to use this tool (any time you need an overview of the toolkit's MCPs and their status). However, it does not explicitly mention when not to use it or name alternative tools. With siblings like 'connect' and 'authenticate', the context makes its purpose obvious, but it lacks explicit exclusions or alternative references.

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