Procuradoria Geral do Estado MT: Dívida Ativa

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

Discloses two authentication modes (permanent vs session) and that token is optional, adding context beyond annotations. Does not mention effects on existing sessions or response behavior, but covers key behavioral aspects.

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 but informative paragraph that front-loads purpose and provides practical usage details. Slightly dense but no fluff; every sentence contributes 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?

No output schema, so description should clarify return values. It mentions 'get the link' for no-args call but does not state what happens when token is passed (e.g., success message or error). Lacks explicit return info, leaving a gap.

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 no description (0% coverage), but description fully explains the 'token' parameter: it is optional, expected to be a JWT, and its use in session login. Compensates for schema gap thoroughly.

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 is for authentication, with specific instructions on browser login and token usage. It distinguishes itself from siblings by focusing on auth flow for IDE agents.

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?

Explicitly explains when to use config header for permanent access versus session-only token paste, and instructs to call with no args to get the login link. Provides clear scenarios and alternatives.

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 readOnly, idempotent, and non-destructive behavior. The description adds meaningful conditional behavior: it explains what happens when providers are connected (authenticated:true, empty pending[]) and when credentials are missing (connect_url and per-install URLs). This goes beyond the structured 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?

Two sentences deliver all essential information with no waste. The first sentence states the core function, the second elaborates the conditional behavior.

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 tool with no output schema, the description fully captures the tool's behavior under both relevant conditions (connected vs missing credentials). It is sufficiently complete for an AI agent to understand the tool's purpose and expected outputs.

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 trivially 100%. The description appropriately does not need to explain parameters; baseline for 0-parameter tools 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 uses a specific verb+resource: 'Returns connection status and URLs'. It clearly defines the tool's purpose and differentiates it from siblings like 'authenticate' by focusing on status checking rather than initiating authorization.

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?

Usage is implied: the tool is for checking connection status. However, there is no explicit statement about when to use this versus 'authenticate' or other siblings, and no enumeration of situations where this tool is or isn't 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?

Beyond the annotations, the description discloses key behaviors: invoke runs one-off without installing or bloating the toolkit, returns a connect link for missing credentials, returns a checkout/top-up link for empty wallets, and requires workspace owner/admin for writes. These details go well beyond the structured annotations and contain no 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 dense and front-loaded with the most important information, and nearly every sentence adds value. It is, however, one long unbroken paragraph that mixes marketplace mechanics with prompt-library details, so structure could be improved for faster 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?

For a complex 14-action, 23-parameter tool with no output schema, the description covers the main flows, permission requirements, auth/payment edge cases, and the prompt library. It omits the 'resume' action and does not detail every return shape, but it is substantially complete for selecting and invoking the 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?

With 0% schema description coverage and 23 parameters, the description must compensate, and it does explain the core action flow and key parameters like mcp_id, tool_id, and arguments. However, many parameters remain unexplained, including limit, immediate, tier_slug, cancel_reason, report_context, request_details, and the prompt_targets array, leaving gaps for an agent.

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 opens with 'official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly defining the resource and its dual role. It enumerates concrete actions (search, describe, invoke, install, list_tools) and distinguishes itself from sibling tools by focusing on discovery and execution of MCPs.

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 an explicit core flow: search → describe → invoke, and gives clear when-to-use guidance for invoke vs install ('prefer invoke for a single/occasional use; use install only to make an MCP PERMANENT'). It also clarifies list_tools, subscribe/cancel, report_bug, and request_mcp, making it easy for an agent to choose the right action.

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=true, idempotentHint=true, destructiveHint=false. The description complements this by disclosing that it is a paid service with prepaid credit, that no platform credentials are needed, and that the client is the data controller under LGPD. This adds value beyond the annotations by clarifying operational and legal aspects. No contradiction detected.

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 of three sentences. It is concise and front-loaded with the tool's purpose. However, it includes additional context (LGPD, payment) that, while useful, is not essential for tool invocation. It could be slightly more structured, but overall it is efficient with minimal waste.

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 six optional parameters and no output schema. The description explains the source, payment model, and legal compliance, which provides a good overview. However, it does not clarify expected inputs (which parameter combinations are valid, required formats, pagination via 'pagina') or the nature of the response (e.g., debt details, status codes). Given the absence of output schema and parameter descriptions, the description is not fully complete for effective invocation.

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 lists six parameters (cda, cpf, cnpj, chassi, pagina, renavam) with no descriptions. The tool description does not explain any of these parameters, their formats, or usage. Schema description coverage is 0%, and the description fails to compensate. The parameter meanings can be inferred from typical Brazilian debt queries, but the agent receives no explicit guidance.

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 for consulting Dívida Ativa (active debt) in the official source of the Mato Grosso State Attorney General's Office. It distinguishes from generic tools by specifying the government entity and the type of query, though it does not explicitly differentiate from sibling tools (which are unrelated infrastructure 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 explains that the tool queries official Brazilian sources and is not for confidential data, and mentions payment via prepaid credit. It implies usage for legitimate debt verification but does not provide explicit when-to-use or when-not-to-use scenarios or alternative tool references. Given siblings are unrelated, some context is provided but exclusions are missing.

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 signal non-read-only and non-destructive behavior; the description adds a small but relevant detail about including conversation data for reproduction. It does not delve into side effects or authentication, but it doesn't contradict annotations and provides a modest amount of additional context.

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 extremely concise, using only two sentences to convey purpose and a key usage tip. Every word earns its place, with no fluff or repetition, making it highly scannable and effective.

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 description captures the essential purpose and the important detail about including conversation data, but leaves some gaps. The 'context' parameter is unexplained, and there's no mention of what happens after submission. Given the tool's simplicity, this is acceptable but not exhaustive, warranting a moderate score.

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 parameter clarity. It mentions the 'conversation' parameter directly, but leaves 'message' and 'context' unexplained. Given the low coverage, the description only partially addresses the parameters, falling short of what is needed.

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 with specific verbs and resources: "Report a bug, missing feature, or send feedback." It effectively communicates what the tool does, though it doesn't explicitly differentiate from sibling tools by name, it is unambiguous in its 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?

Provides clear usage guidance: "Include the conversation array with recent messages for reproduction." This tells the agent what to do when calling the tool, though it doesn't mention when not to use it or name alternatives, it gives actionable context for correct invocation.

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 mark it as readOnly and idempotent with no destructive side effects. The description adds no conflicting information, and the behavior is straightforward and transparent.

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, directly conveying the tool's action without any fluff or unnecessary detail.

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 absence of parameters and output schema, the description fully specifies the tool's behavior. It is complete for its simplicity.

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 no parameters, and the description correctly does not reference any. No additional parameter meaning is needed.

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: displaying current MCP platform and adapter versions. It is specific and distinguishes this simple query tool from sibling tools like connect or authenticate.

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?

While no explicit when-to-use guidance is given, the purpose is self-evident and complements the sibling tools. The description implicitly indicates it is for checking version information, which is clear enough for typical 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, idempotentHint, and destructiveHint=false, so the safety profile is well established. The description adds useful behavioral context by specifying exactly what kind of state information is returned, going beyond a bare 'returns toolkit info' statement.

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 core purpose ('Returns the current toolkit state') and then lists the key data points. There is no wasted wording or redundant detail.

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 strong annotations, the description sufficiently covers what the tool returns. It names the main categories of information an agent would need to know before invoking it, making the tool's behavior adequately predictable.

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 input schema is empty, so there are no parameter semantics to document. Per the rubric, a zero-parameter tool receives a baseline of 4, and the description does not need to compensate for any unknown schema coverage.

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') and a clear resource ('current toolkit state'), then enumerates exactly what is included: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from action-oriented siblings like authenticate, connect, and report_bug.

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 when to use this tool: when an agent needs to inspect the current state of the toolkit, including connections and installed MCPs. It does not explicitly state exclusions or alternatives, but the context is clear enough that no alternative tool would be confused with this read-only status function.

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