Prefeitura SP São Paulo: Certidão Tributária Mobiliária

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

Description discloses behavior: returns link if no token, authenticates with token, and differentiates permanent vs session outcomes. Annotations (readOnly=false, destructive=false, idempotent=true) are not contradicted; description adds valuable context about user interaction and persistence.

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?

Description is somewhat verbose but organized into clear segments (MCP.AI, Best, Or). It avoids redundancy and each sentence adds necessary detail. Slightly longer than ideal but justified by the dual-mode explanation.

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 no output schema, description covers the full user journey: initial login, token acquisition, two ways to use the token, and the effect of each. It provides enough context for an agent to decide and execute correctly.

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 single 'token' parameter is not described in the schema, but the description explains it as the JWT copied from browser, and clarifies that it's optional (no args triggers link retrieval). This fully compensates for the lack of schema description.

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?

Description clearly states the tool authenticates by obtaining a token, with explicit steps and two usage modes (permanent via config or session via token). It distinguishes itself from other tools like connect or marketplace by focusing on authentication.

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 instructions: log in browser, copy token, then either add to config for permanent or pass token for session. Also explains the no-args behavior (get link). Clearly indicates when and how 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?

The description adds rich behavioral context beyond the annotations by explaining the response in different states: 'When all providers are connected' vs 'When credentials are missing'. It details what fields to expect (authenticated:true, pending[], connect_url) which is very helpful. This goes beyond the readOnlyHint and idempotentHint annotations, providing concrete behavioral expectations.

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, using exactly two sentences to convey both the primary purpose and the two most important execution states. Every clause adds value: the first sentence states the return type, and the second explains conditional outputs. No unnecessary words 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?

For a 0-parameter, read-only status tool, the description provides a complete picture. It covers the main behavioral branches (all providers connected vs. missing credentials) and their corresponding outputs. No output schema exists, so the description appropriately explains return values. Given the simplicity of the tool, this is fully sufficient.

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?

There are zero parameters, and the JSON schema correctly reflects this with an empty properties object, so schema coverage is trivially 100%. Per the rubric, 0 params gives a baseline of 4. The description does not need to explain any parameter semantics, which would be redundant here.

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 with a specific verb and resource: 'Returns connection status and URLs.' It distinguishes itself from siblings by describing the output states (authenticated:true, pending[], connect_url) and is clearly different from 'authenticate' or 'show_version'. The scope is unambiguous and immediately conveys what the tool does.

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 over siblings or specify exclusions. No alternatives are mentioned, but the purpose is clear enough that a user can infer when this is appropriate. Lacks explicit guidance such as 'use this if you need to verify connectivity' or 'instead of authenticate'.

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?

With no meaningful behavior info in the annotations, the description carries the disclosure burden and does well: invoke works even when the MCP is not installed, may return a connect link or checkout/top-up link, and writes require workspace owner/admin. It does not describe side effects of resume/uninstall or rate-limit behavior, so it is not a 5.

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 information-dense and all sentences contribute, but it is long and written as one continuous prose block with ALL-CAPS emphasis and a mixed-language example. Grouping by action flow with bullets would make it more scannable for an agent.

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 23-parameter tool with no output schema, the description covers the main workflows, auth constraints, install vs invoke semantics, and key link behaviors. The gaps are the unmentioned resume/uninstall actions and some lesser-used parameters, but the overall context is strong.

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 23 parameters with 0% description coverage, so the description must compensate; it explains action, mcp_id, tool_id, arguments, and the prompt-library parameters at a high level. However, many parameters such as immediate, tier_slug, conversation, cancel_reason, report_context, and request_details are left entirely to their names and defaults.

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 catalog plus a way to run MCPs, and walks through the search/describe/invoke flow. It is less crisp than a single-purpose tool because it also bundles the prompt-library actions and overlaps with the sibling report_bug tool, but the core purpose is unmistakable.

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 guidance: prefer invoke for one-off use, use install only for permanent toolkit membership, use request_mcp when nothing fits, and use subscribe/cancel for billing. It also states the owner/admin requirement for writes, which is strong when-to-use/when-not-to-use 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, and destructiveHint=false, so the safety profile is clear. The description adds useful context: it's hosted by the platform, requires pre-paid credit per query (disclosing a billing behavior), and clarifies data privacy (non-confidential, client is data controller under LGPD). This goes beyond annotations to disclose operational and legal requirements.

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

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

The description is a single sentence of moderate length, but it packs multiple pieces of information (purpose, hosting, payment, data source, LGPD) without clear structure. It reads as a run-on and could be more front-loaded with the core query action, followed by contextual notes. It is not overly verbose, but the structure is not optimal.

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 there is no output schema and the tool queries a specific public certificate, the description is missing key details: it does not specify what response looks like, whether both CPF and CNPJ are needed, or whether there are any prerequisites (e.g., pre-paid credit balance). It does mention LGPD responsibilities, but the practical usage context is incomplete for a paid, hosted 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?

Schema description coverage is 0%, and there are two parameters (cpf and cnpj) with no descriptions in the input schema. The description does not explain how to provide these identifiers, whether one or both are required, or their format. It mentions 'pague por consulta' but does not clarify which parameter is used for a CPF vs CNPJ query. The description fails to compensate for the lack of schema guidance, leaving parameter semantics unclear.

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 that this tool consults the São Paulo municipal tax certificate (Certidão Tributária Mobiliária) from an official source, with the verb 'consultar'. While it mentions the city and source, it doesn't explicitly differentiate from other similar consultation tools beyond naming the specific certificate type, so it lacks explicit sibling differentiation.

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 about when to use it (to query official Brazilian sources, same as available to citizens) and mentions payment via pre-paid credits, but it doesn't explicitly state when not to use it or alternative tools. It implies usage for non-confidential data and LGPD compliance, but lacks clear 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 idempotentHint=true, readOnlyHint=false, and destructiveHint=false, so the safety profile is known. The description adds the detail about including conversation for reproduction, which provides some behavioral context, but it does not describe side effects or expected responses. This is acceptable but not extensive beyond 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 two concise sentences, front-loaded with the purpose and a key usage hint. No unnecessary words or repetition; it is entirely effective for 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?

For a simple tool with three parameters and no output schema, the description gives a clear action and the key reproduction requirement. However, it does not explain the roles of all parameters (context, message) explicitly, which is a minor gap. It is minimally adequate but could benefit from a one-line parameter explanation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the three parameters. It mentions the conversation array but does not clarify the 'message' or 'context' fields. It implies 'message' is the content via 'report a bug' but lacks explicit definitions or format guidance, leaving the agent with incomplete information.

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

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

The description clearly states the tool's purpose: 'Report a bug, missing feature, or send feedback.' This is a specific verb (report) with explicit resource types, and it distinguishes itself from sibling tools like authenticate or marketplace by addressing feedback/bug reporting.

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 no guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. It only instructs to include the conversation array, which is a usage detail but not context for choosing the tool.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well-covered. The description adds that it shows versions, which is consistent. However, it doesn't specify the output format or whether it returns structured data, but for a simple version tool this is acceptable given 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 sentence with no unnecessary words. It is concise and directly states the purpose without any fluff. The structure is optimal for a simple tool.

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 no parameters Scott, and the annotations fully cover its safety profile (read-only, idempotent, non-destructive). The description clearly indicates what information it provides. There is no output schema, but for a version-query tool, the expected output (version strings) is self-evident. Thus, it is complete for its intended use.

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 covers 100% of what is expected. With no parameters, there is nothing to document, and the schema's empty properties object is fully adequate. The description adds no extra parameter context because none exist.

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: showing the current MCP platform and adapter versions. It uses a specific verb ('show') and explicitly names the objects (platform and adapter versions), leaving no ambiguity about what the tool does.

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?

Being a no-parameter tool, there are no usage instructions needed. The description inherently signals when to use it (when version info is required), and there are no prerequisites or special conditions to mention. The tool's self-explanatory nature fully covers usage 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 declare readOnlyHint=true and idempotentHint=true, which already signal a safe, non-destructive operation. The description adds specific details about what information is returned (installed MCPs, connection status, accounts, catalog tool counts), which helps the agent know what to expect beyond the annotation hints.

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 lists the key output components. It is front-loaded with the main purpose and adds minimal but valuable detail. No unnecessary words.

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, a simple read-only info retrieval, and strong annotations, the description is complete. It covers what the tool returns. An output schema is absent, but the tool is simple enough that the description suffices. A minor gap: it doesn't mention the format or structure of the return value, but this is not critical for an info 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 0 parameters, and the schema coverage is 100% (no properties). The description does not need to explain any parameters. The absence of parameters is evident from the schema, and the description's focus on return content is appropriate. Baseline for 0 params is 4.

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 exactly what the tool does: returns the current toolkit state, listing installed MCPs, their connection status, associated accounts, and catalog tool counts. This clearly distinguishes it from siblings like connect or authenticate, which have different verbs and resources.

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 it (to inspect toolkit state) but does not explicitly state when not to use it or name alternatives. It is clear enough for an agent to infer usage, but lacks explicit guidance on alternatives or exclusionary scenarios.

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