Conselho Nacional de Justiça SEEU: Processos

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

The description mentions behavioral aspects like the permanence of the connection ('permanent, non-expiring') and the browser-based login flow, but it doesn't explicitly disclose potential side effects (e.g., storing tokens, network calls) or the exact response format. The annotations (idempotentHint=true) are not contradicted, and the description adds some context, but more could be said.

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, run-on passage with multiple clauses, parentheses, and semicolons, making it harder to parse. It mixes setup tips with invocation instructions and could be reorganized into clear bullet points or sentences. While informative, it lacks conciseness and structure.

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 is relatively simple with one optional parameter and no output schema. The description covers all the key usage patterns (passing a token, omitting it, obtaining a link) and the context for IDE agents. A few gaps remain (e.g., what the tool returns or whether it prompts a browser), but overall it's sufficiently complete for an agent.

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 only defines an optional 'token' string with no description, and the parameter coverage is 0%. The description fully compensates by explaining that 'token' should be a JWT for session-only login, and that calling with no arguments returns a link. This is essential information not available elsewhere.

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 indicates that the tool handles authentication/login for IDE agents, mentioning 'log in in the browser' and access tokens. However, it is presented as a series of steps rather than a concise statement, and fails to distinguish from the sibling tool '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 usage context: it's for IDE agents like Cursor, with two distinct modes (permanent config via header or session-only token). It explains when to pass a token versus when to omit it, and even notes the 'no args to get the link' case. However, it doesn't explicitly discuss alternatives or contrast with sibling tools.

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 valuable context beyond annotations: the cost model (prepaid per query), authentication requirements (no platform credentials), data classification (public, not confidential), and LGPD compliance responsibilities. 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 a single run-on sentence mixing purpose, payment terms, data classification, and LGPD legal language. It is not well-structured and lacks front-loading. While not excessively long, the dense, comma-separated clauses reduce readability.

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 5 optional parameters and no output schema, the description should explain what information the consultation returns, how to form a valid query (e.g., at least one identifier), and any limitations. It covers source, payment, and data type, but omits query semantics and output expectations, making it incomplete for correct 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 description coverage is 0%, so the description must compensate for parameter meaning. It does not explain any of the five parameters (cpf, cnpj, nome_mae, nome_parte, numero_processo), whether at least one is required, or how they can be combined. This is a major gap for a tool with no required 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 identifies the tool as a consultation for CNJ SEEU processes from an official source, using 'consulta' as the verb and 'Processos' as the resource. It is clear but could be more specific about what process data is returned. No sibling tool offers similar functionality, so differentiation is not needed.

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 useful usage context: no platform credentials needed, prepaid credit per query, and the data is the same public information available to citizens. It does not explicitly state when to prefer this tool over alternatives, but there are no relevant alternatives among the siblings, so clear context suffices.

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 and idempotent behavior. The description adds valuable behavioral context by explaining the output differences based on connection state (authenticated:true vs connect_url), going beyond what annotations provide.

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 main purpose, and then explains the conditional behavior. There is 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 status tool with no parameters and no output schema, the description covers both possible outcomes and the relevant returned data. It is self-contained and sufficient for an agent to understand 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?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and it appropriately focuses on output behavior instead.

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 detail on the two possible states (all connected vs. missing credentials). It distinguishes itself from siblings like 'authenticate' by focusing on status retrieval rather than authentication 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 implies usage (checking connection status) but does not explicitly state when to use this tool over alternatives, nor does it mention exclusions or prerequisites. There is no reference to sibling tools or 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?

Beyond annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses critical behavioral details: invoke runs one-off without installing, returns connect/checkout links on auth/funding issues, flags installation states, and requires owner/admin for writes. This adds rich context and 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 long (around 300 words) but every sentence adds value, covering the core flow, specific behaviors, and usage distinctions. It is well-structured with 'KEY:' and clear demarcations between marketplace and prompt library. While not concise, it is efficiently packed and front-loaded with the most critical info.

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 no output schema, the description must convey expected outcomes. It explains returns for search/describe/invoke (e.g., full profile, connect/checkout links) but does not describe response structures comprehensively. The 23 parameters and 14 actions are broadly covered, and the description is adequate for a complex meta-tool, though some niche actions lack detail.

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 23 parameters and 0% schema description coverage, the description must compensate. It explains the semantic meaning of `action` values and the flow involving `query`, `mcp_id`, `tool_id`, `arguments`, and prompt-related params. However, it does not detail every parameter (e.g., cancel_reason, immediate, tier_slug), leaving gaps, but the coverage of the core action enum and key fields is substantial.

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 the official mcp.ai marketplace, catalogs all MCPs, and facilitates running them. It distinguishes its actions (search, describe, invoke, install) and explicitly contrasts with siblings like connect and authenticate by being the central discovery/execution hub.

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 extensive when-to-use guidance: 'prefer invoke for a single/occasional use', 'use install only to make an MCP PERMANENT', and explains the core flow (search → describe → invoke). It also clarifies when to use list_tools, subscribe/cancel, and the prompt library actions, with explicit exclusions for 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 cover read/write intent, idempotency, and destructiveness. The description adds minor behavioral context by instructing the agent to include the conversation array for reproduction, implying input collection. It does not explain side effects or return behavior, but annotations carry the safety profile.

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 short sentences, front-loaded with the primary purpose. The second sentence provides necessary repro detail without padding. No wasted 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?

For a simple 3-parameter tool, the description is adequate but not fully complete: it mentions the purpose and a key input (conversation), but doesn't clarify the 'message' or 'context' parameters, or explain the result/return behavior. Since there is no output schema, a bit more detail would increase 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 zero schema description coverage, the description had to compensate. It only glosses over the 'conversation' parameter ('Include the conversation array with recent messages'), leaving 'message' and 'context' unexplained. The required 'message' parameter is not named or semantically clarified in the 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?

The description uses a specific verb ('Report') and identifies the resource (a bug, missing feature, or feedback), clearly distinguishing this tool from the listed sibling tools. It expands beyond the tool name to cover three specific use-case types.

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 context for when to use the tool: for bugs, missing features, or feedback. It does not explicitly mention alternatives or exclusions, but no sibling appears to serve the same reporting function, so the context is clear enough.

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 HTTPS. The description adds no extra behavioral context (e.g., output format, latency). It neither contradicts nor enhances the annotations, so a moderate score of 3 is appropriate.

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 sentence with zero filler. Front-loaded and precise. Every word earns its place.

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 check tool, the description suffices without additional details. It states the subject (MCP platform and adapter versions). Annotations cover safety and idempotency. No output schema exists, but what it returns is clear from the description. Complete for its complexity.

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 is fully documented (empty schema). The description mentions 'platform and adapter versions' which hints at the return content but adds no parameter semantics, since there are none. Baseline 4 for 0 params is appropriate.

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 shows current MCP platform and adapter versions, with a specific verb 'Show' and a clear resource. It distinguishes itself from siblings like connect or report_bug, which have different purposes.

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 self-evidently for checking versionsUTE. No explicit when-to-use or alternatives are mentioned, but given the simple read-only nature and sibling tools, the context is clear enough. However, lacking any exclusion guidance keeps it at a baseline 3.

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 cover safety (readOnlyHint=true, idempotentHint=true, destructiveHint=false). The description adds content about what is returned, which is beyond annotations, but does not disclose additional behavioral traits such as authentication requirements or network dependency. Given annotation coverage, this is acceptable, though not richly descriptive.

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 redundancy or extra fluff. Every word contributes to clarifying the tool's output, making it highly concise and 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?

The description fully explains what the tool returns, given its simplicity. There are no parameters or output schema to complicate matters. The annotated read-only and idempotent hints confirm safe operation, and the description covers the core information need completely.

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 schema is trivially complete and the description adds no parameter meaning. Per guidelines, a baseline of 4 applies for zero-parameter tools; the description appropriately does not need to compensate for 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: returning the current toolkit state, and enumerates specific contents (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools like connect or authenticate, which have different functions.

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 does not explicitly state when to use this tool versus alternatives. However, its purpose as a read-only status query is self-evident, and siblings like connect or authenticate are obviously different in intent. No explicit when-not or alternative guidance is provided, so it relies on context.

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