Antecedentes (Polícia Civil)

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds behavioral context beyond annotations: no authentication is needed, each query consumes prepaid credit, and the data is public access. It also explains the data privacy role under LGPD, which is useful for agent decision-making.

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 few clear sentences in Portuguese, front-loaded with the main function. It includes relevant details about cost, credentials, and data publicness. The LGPD sentence is somewhat tangential but still pertinent for compliance. Overall, it is efficient and well-structured 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?

The tool has 7 parameters and no output schema. The description covers purpose, target user, data nature, access model, and cost, which is good context. However, it omits parameter semantics and does not mention what the tool returns (e.g., the certificate content or a status). This is a moderate gap given the absence of an output schema.

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 descriptions are absent (0% coverage), so the description must compensate. It names only CPF, RG, UF, and nome, but the schema requires NomeMae, DataNascimento, and includes an optional 'completo' flag, which are not explained. This partial coverage leaves the agent without guidance on required fields or the meaning of 'completo'.

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 explicitly states it queries the criminal record certificate ('certidão de antecedentes criminais') from the Civil Police, using CPF, RG, UF, and name. It also clarifies the intended user (the record holder), which distinguishes it from background-check tools and clearly differentiates it from sibling platform 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 clear usage context: it is intended for the data subject to consult their own records, it requires no credentials but charges prepaid credit, and it imposes LGPD responsibilities on the client. It does not explicitly state when not to use the tool or reference alternatives, but sibling tools are unrelated, so the guidance is adequate.

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 annotations, the description reveals key behaviors: token is a JWT, can be permanent or session-only, and calling with no args returns a login link. It does not contradict readOnlyHint: false or idempotentHint: true, and it adds meaningful context about token lifetime and configuration.

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 three sentences long with a clear structure ('Best:' and 'Or') that makes it easy to follow. While it is a bit wordy, every sentence adds value, so it earns a 4 rather than a 5.

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 one optional parameter and no output schema, the description is complete: it covers the authentication workflow, configuration options, token semantics, and what to expect (a link) when calling with no args. It fully equips the agent to use the tool 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 schema provides only 'token: string' with no description. The description compensates fully by explaining the token's format (JWT), its optionality, and exact usage: call with { token: '<jwt>' } or with no args to get the link. This is excellent semantic 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 opens with 'MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token,' clearly identifying the tool's purpose as authentication. It distinguishes itself from siblings like 'connect' by focusing on token-based login 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?

The description provides explicit usage guidance: 'Best: add it to this server's config as a header ... for a permanent, non-expiring connection' and 'Or paste it here for a session-only login.' It gives clear context for two methods but does not explicitly mention when not to use the tool or alternative tools, hence 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 already declare read-only and idempotent behavior. The description adds valuable context about conditional responses based on connection state (authenticated vs. missing credentials), which goes beyond the annotations. It does not mention side effects or required auth, but these are covered by the 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 sentences, front-loaded with the core purpose, and every sentence provides useful information without redundancy or fluff.

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 simplicity of the tool (no params, no output schema), the description covers the main expected outcomes. However, it only describes the two extreme states (all connected vs. credentials missing) and does not address partial connection states, which could be a minor 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?

The tool has zero parameters, so there is no parameter information to add. Per baseline, a description is not expected to compensate for parameter documentation when there are none. The description correctly focuses on 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 the tool returns connection status and URLs, with specific conditions for different outputs. It distinguishes itself from siblings like 'authenticate' by focusing on status checking rather than performing 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?

The description implicitly explains when to use this tool: it tells the user what to expect when credentials are missing, implying this is the tool to check current connectivity. However, it does not explicitly name alternatives or state when not to use 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?

Goes well beyond annotations by disclosing key behaviors: invoke works even when MCP is not installed, runs the tool 'pontualmente (one-off)' without adding to toolkit, returns connect/checkout links for auth/payment with retry instruction, and writes require workspace owner/admin. 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 appropriately structured: summary sentence, core flow with arrows, key invoke behavior, billing/permissions, prompt library. It's dense but every section adds value for a 14-action tool; it could be split into bullets for easier scanning but remains 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?

Given the tool's complexity (14 actions, 23 parameters), the description covers most critical behaviors: search/describe/invoke/install, billing, prompts, and permissions. However, it omits explanation of the 'resume' action and some parameters, and with no output schema it doesn't specify return structures (beyond the connect/checkout links), leaving minor gaps.

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 by explaining the action enum semantics and several key parameters (mcp_id, tool_id, arguments, prompt_*). However, some parameters like 'immediate', 'tier_slug', 'conversation' are left unmentioned, though many are self-evident from their names.

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 role: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It distinguishes itself from siblings by covering a wide range of actions (search, describe, invoke, install, prompts) with a coherent core flow, whereas siblings like authenticate/connect are narrowly scoped.

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 guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It outlines a step-by-step flow (search → describe → invoke) and explains when to use other actions (list_tools, subscribe/cancel, report_bug, request_mcp, prompt actions). Also clarifies permission requirements for writes.

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, destructiveHint=false, and idempotentHint=true, so the description doesn't need to restate these. It adds context about including the conversation array for reproduction, but doesn't disclose what happens after reporting (e.g., ticket creation). No contradiction found.

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 with no fluff. It wastes no words and delivers the core instruction clearly.

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 params and no output schema, the description covers the primary purpose and one key parameter. However, it leaves 'message' and 'context' semantics vague and doesn't mention expected outcomes or side effects beyond what annotations imply.

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 adds some meaning for the 'conversation' parameter ('Include the conversation array with recent messages for reproduction') but leaves the required 'message' and optional 'context' unexplained, providing insufficient 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's purpose with a specific verb ('Report') and resource (bug/feature/feedback). It distinguishes itself from unrelated sibling tools like 'authenticate' and '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?

It provides a clear when-to-use guideline ('Report a bug, missing feature, or send feedback') and instructs the agent to include the conversation array. However, it doesn't explicitly mention alternatives or exclusions, though siblings are unrelated.

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 established. The description adds behavioral context by specifying 'current' versions and narrowing scope to MCP platform and adapter versions, which is useful beyond the annotation-only view. It does not contradict any annotation.

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, directly front-loaded with the action and object. Every word adds value, with no repetition of the name or unnecessary qualifiers. It is optimally concise.

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 annotations covering read-only/idempotent behavior, the description is sufficient for an agent to select and invoke it. The only missing detail might be the return format, but for a version tool this is not a critical gap. The combination of description and annotations makes the tool's behavior fully 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, so the input schema is fully covered at 100% and there is nothing for the description to add. Per the baseline for 0-parameter tools, this is appropriately scored as 4. The description correctly omits parameter details since 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 uses a specific verb 'show' and clearly identifies the resource: 'current MCP platform and adapter versions.' It is unambiguous and distinct from siblings like toolkit_info, which would cover broader toolkit information. No confusion about what this 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 the tool is for checking version information, but it does not explicitly compare to sibling tools like toolkit_info or state when to use this instead of alternatives. However, the tool's purpose is self-evident and there is little ambiguity in a version-checking 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. The description adds meaningful context by specifying exactly what state information is returned (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotations and gives the agent a clear expectation of the tool's output.

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 that is front-loaded with the main action ('Returns the current toolkit state') and then efficiently lists the included elements. Every word contributes value, with no redundancy or filler.

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, zero-parameter, read-only tool with no output schema, the description fully covers what the agent needs to know: what the tool does and what information it returns. The annotations cover the safety profile, so nothing else is needed.

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 description doesn't need to explain parameter usage. The baseline for 0-param tools is 4, and no additional parameter information is required.

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's function with the verb 'Returns' and specifies the resource: the current toolkit state. It enumerates exactly what is included (installed MCPs, connection status, accounts, catalog tool counts), which distinguishes it from sibling action-oriented tools like authenticate or connect.

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 clear context that this is a state-inspection tool, implying it should be used when you need an overview of the toolkit's MCPs, connections, and accounts. It does not explicitly name alternatives or exclusions, but the nature of the tool makes its use case obvious and distinct from the action-oriented siblings.

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