Conselho Nacional de Justiça: Mandados de Prisão

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

It adds meaningful behavioral context beyond the annotations: the description distinguishes a permanent, non-expiring connection (config header) from a session-only login (token argument), and explains that no-args returns a login link. There is no contradiction with the supplied readOnlyHint, openWorldHint, idempotentHint, or destructiveHint values.

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 and front-loaded, delivering the login instruction in the first sentence and then clarifying permanent versus session-only access. It is only slightly awkward in phrasing ('log in in the browser' and the repeated 'paste' verbs), but it remains 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 one-parameter, no-output-schema tool, the description covers the main scenarios: no-args for link, token for session-only login, and config header for permanent access. It does not explicitly state what a successful token call returns or how failures are reported, but overall completeness is solid.

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 only declares token as a string with no description, so the description carries the responsibility. It explains the token is a pasted JWT/access token and clarifies the no-arguments case, which the schema alone would not reveal.

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?

It clearly describes the tool as an authentication/login operation for the MCP server: log in via browser, obtain an access token, and either configure a permanent header or send a session token. It is explicit about the auth flow but does not directly contrast with sibling tools such as connect, although the purpose is distinct.

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 concrete usage guidance: call with no args to get the link, call with { token: "<jwt>" } after the user pastes the token, or instead configure the Authorization header for permanent access. It is clear on invocation modes but does not explicitly discuss when not to use this tool or when to prefer a sibling.

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. The description adds value by disclosing payment requirements (prepaid credit), that data is not confidential, and the client is LGPD data controller. No contradiction; it enriches behavioral 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 a single paragraph of four sentences, front-loading the purpose. It covers essential operational details (payment, LGPD) without significant redundancy. Slightly verbose but appropriate for the regulatory context.

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 3 optional parameters and no output schema, the description is incomplete: it does not describe what data is returned, expected output format, or any parameter semantics. It also fails to clarify optional vs required filters. The LGPD/payment context is helpful but not sufficient 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?

Schema has 3 parameters (cpf, nome, nome_mae) with 0% description coverage. The description does not explain any parameter's purpose, format, or which are needed. It falls far short of compensating for the schema gap, offering no guidance on how to construct a valid query.

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 queries official Brazilian arrest warrants from the CNJ, with a specific verb 'consulta' (query) and resource 'Mandados de Prisão'. It distinguishes from sibling tools (authenticate, connect, etc.) which are generic 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?

Provides clear context: official source, no platform credentials needed, pay-per-query with prepaid credit, and LGPD compliance. It implies when to use (need to check arrest warrants) but does not explicitly exclude alternatives or state when not to use, 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?

The description provides two specific scenarios (all connected and missing credentials) but does not cover other possible states (e.g., partial connectivity, errors). The absence of an output schema and limited state detail reduces transparency. However, the readOnlyHint and idempotentHint align with the description, indicating no side effects.

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 highly concise, conveying the behavior and expected outputs in two sentences without unnecessary verbosity. It is efficient and to the point.

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 (no params, read-only), the description covers the main use case but lacks explicit details about partial connection states, error handling, or the structure of per-install URLs. The absence of an output schema means consumers must infer structure. Still, it is adequate for a basic status check 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 zero parameters (no input schema required). With no parameters to document, the description covers all applicable parameters. The 100% schema description coverage and clarity of the output are sufficient.

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: 'Returns connection status and URLs.' It also explains the two primary states (all connected vs. missing credentials), making the 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 implicitly indicates when to use the tool (to check connection status), but does not explicitly state prerequisites or typical invocation scenarios. Given it has no parameters and is read-only, the guidance is sufficient but could mention it as a first-step diagnostic.

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?

No annotation contradiction; readOnlyHint=false is consistent with the description's write behavior (install/uninstall/subscribe/cancel). The description adds rich context beyond annotations: one-off invoke without toolkit bloat, auth tie to connect links, wallet-empty checkout flow with retry, workspace owner/admin requirement for writes, and the no-login shareable prompt link.

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 content is valuable but formatted as one dense, run-on paragraph with no section breaks for the 14 distinct actions. Some redundancy exists (one-off install behavior is stated twice: 'without adding the MCP...without bloating' and later 'prefer invoke for a single/occasional use'). Length is justified by complexity, but structure hurts scannability.

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 dispatcher without an output schema and with bare annotations, this description is remarkably complete: it explains the discovery-to-execution flow, edge cases (auth needed, empty wallet), ownership permissions, the distinction between one-off and permanent installs, and the entire prompt-library subsystem with its sharing behavior. Little that an agent needs is left unexplained.

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 coverage and 23 parameters, the description must compensate heavily. It does: the action enum is fully explained, tool_id and mcp_id flow is described ('pick the right tool_id → invoke RUNS that tool'), prompt params are tied to their functions. However, several params (limit, immediate, tier_slug, cancel_reason, cancel_comment, prompt_vars, conversation, prompt_targets) get no explicit semantic coverage, leaving a meaningful gap.

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 a very specific purpose: 'the in-platform catalog of every MCP/tool, AND the way to run them,' with a concrete action flow (search→describe→invoke). It distinguishes its core from sibling tools like toolkit_info and authenticate by framing itself as the discovery+execution dispatcher, and it names distinct capabilities (prompt library) that no sibling covers.

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?

Extremely explicit guidance: 'Use install only to make an MCP PERMANENT in the active toolkit...prefer invoke for a single/occasional use,' with the core flow spelled out step-by-step, alternatives named (list_tools for what's callable now, request_mcp for building new MCPs), and clear failure/retry behavior (connect link, checkout link, then retry).

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 indicate idempotentHint=true, readOnlyHint=false, and destructiveHint=false, but the description does not add behavioral context. It doesn't mention side effects (e.g., creating a ticket), permissions, rate limits, or what happens after submission. Since the description only states the action without disclosing underlying behavior, transparency is limited.

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, consisting of two sentences without unnecessary verbosity. It is well-structured and to the point. However, it could benefit from a brief list of parameters or a more structured presentation, though the brevity is generally appropriate.

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 simple schema (three strings, no output schema, no nested objects), the description is incomplete. It fails to explain the meaning of 'context' and 'message,' and the instruction about 'conversation array' is vague (and contradicts the string type). The description does not cover return values or error conditions, leaving users uncertain about the tool's full behavior.

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 defines three string parameters (context, message, conversation) with no descriptions. The description only mentions 'conversation array,' but the schema types it as a string, creating ambiguity about the expected format. Moreover, context and message are entirely unexplained. The description adds minimal value for parameter understanding and even introduces a mismatch with the schema.

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') and identifies the resource types (bug, missing feature, feedback). It is distinct from sibling tools like authenticate or marketplace, which handle different functions. The additional instruction about including a conversation array clarifies the expected use case.

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 some usage guidance by instructing to 'Include the conversation array with recent messages for reproduction,' which hints at when to use the tool (e.g., when reporting issues with context). However, it does not explicitly state when not to use it or mention any alternative tools. The guidance is implied rather than explicit, so it falls short 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that the tool reports current platform and adapter version details, but it provides no further behavioral context beyond what the annotations already establish.

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 filler. Every word contributes meaning, making it optimally concise for the tool's simple purpose.

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 minimal complexity—no parameters, no output schema, and strong safety annotations—the description is fully sufficient. It tells the agent exactly what the tool does and what information it returns, so no additional context 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 and 100% schema description coverage, so there is no parameter burden for the description to carry. The description appropriately clarifies what the version information relates to, earning the baseline-4 score for parameterless tools.

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 a concrete resource ('current MCP platform and adapter versions'), so the purpose is clear. It does not explicitly differentiate from sibling tools like toolkit_info, which could potentially overlap, but the resource is precise enough to be understood.

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?

There is no guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. The description implies a simple version-check scenario, but it does not state when the agent should prefer this over sibling tools like toolkit_info.

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 annotations already declare read-only, idempotent, and non-destructive behavior. The description adds specific behavioral details by listing what the returned state includes, but does not go beyond that. This is sufficient given the safety 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, concise sentence that clearly enumerates the returned information without unnecessary words 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?

With no parameters and no output schema, the description provides all necessary context about what the tool does. It fully explains the return value, so no additional information is required.

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, so the schema fully covers them (vacuously). The description adds no parameter information because none 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: it returns the current toolkit state and enumerates the specific components (installed MCPs, connection status, accounts, catalog tool counts). This is a distinct action from the sibling tools, such as 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?

While the description directly implies when to use the tool (whenever you need current toolkit state), it does not explicitly mention alternatives or provide exclusion criteria. However, the purpose is so clear that usage is self-evident, meriting a score above 3.

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