Tribunal TJSP: Processos do 1º Grau

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

The description adds useful behavioral context beyond annotations: it explains that config-based tokens are permanent and non-expiring, while pasted tokens are session-only. It does not detail failure modes or success response formats, but annotations already establish safety 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 fairly compact and front-loaded with the core browser-login flow. The 'MCP.AI for IDE agents' opener and the two-part config-vs-session guidance earn their place, though a slightly cleaner structure would improve it.

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-optional-parameter auth tool with no output schema, it covers the main workflow well: login flow, permanent config option, session-only option, and no-args behavior. It does not specify what the tool returns after token authentication, which leaves some ambiguity, but the description is otherwise adequate.

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 is bare with 0% coverage, and the description compensates by explaining that the optional token parameter is a JWT to be pasted after login. It also makes clear that calling without arguments returns the login link, which adds meaning to an otherwise undocumented parameter.

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 the tool is for authentication: the user logs in via browser, pastes a JWT, or calls with no args to receive a login link. It distinguishes itself by being the auth/token entry point among the listed sibling 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?

It explicitly distinguishes the permanent config-based login from the session-only pasted-token login, and says to call with no args to get the link. It gives concrete branch guidance, though it does not explicitly mention alternatives like 'connect'.

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 and idempotentHint. The description adds valuable conditional behavior ('when all providers are connected...' and 'when credentials are missing...'), disclosing the dynamic response shape. No contradictions.

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 succinct sentences, front-loading the main purpose and then covering edge cases. No 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?

For a read-only, zero-parameter status endpoint with good annotations, the description fully covers the response behavior and failure modes. No output schema 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?

No parameters exist, so schema coverage is trivially 100%. The description doesn't need to add parameter semantics. Baseline 4 applies.

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?

Specific verb+resource: 'Returns connection status and URLs.' Clearly differentiates from siblings like authenticate and toolkit_info. The purpose is immediately obvious.

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 its use as a status check but does not explicitly state when to prefer it over siblings or when not to use it. No exclusions are given, but the context is understandable.

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 are weak (all false), so the description carries full burden. It adds substantial behavioral context: 'invoke works even when the MCP is NOT installed', credential flows ('invoke returns a connect link'), payment flows ('checkout/top-up link... then you retry'), permission requirements ('Writes require workspace owner/admin'), and the 'installed_in_toolkit vs installed_in_workspace' flags. The one-off vs permanent install distinction transparently explains the 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?

This is a single, dense wall of text with no paragraph breaks, lists, or visual segmentation despite covering two major features, ~14 actions, and ~20 concepts. It mixes languages ('consulta um CPF', 'pontualmente') and crams orthogonal concerns (search flow, install-vs-invoke decision, billing, prompt library) into one run-on narrative. The content is valuable, but the structure actively harms scannability for such a complex 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?

Given the extreme complexity (23 params, 14 actions, a sub-feature), the description is dense but comprehensive: it covers auth, payment, permissions, billing lifecycle (subscribe/cancel), error recovery ('then you retry'), and prompt library semantics without an output schema to offload to. Small gaps remain (list_tools output semantics, immediate/tier_slug, search result structure), but the main user journeys and edge cases are addressed.

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 must compensate. It does explain the core action parameter values contextually: 'action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool.' It also explains prompt library parameters like prompt_vars ('with {{variables}} filled') and publish_prompt's slug link. However, many parameters (limit, query, immediate, tier_slug, conversation, cancel_reason, report_context, etc.) remain undocumented in both schema and description, which prevents a 5.

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 — the in-platform catalog of every MCP/tool, AND the way to run them.' It uses the specific verb+resource structure ('discover', 'describe', 'invoke'), defines scope ('Covers capability requests like find an MCP that does X'), and distinguishes the prompt library sub-feature from the MCP catalog. The polysemous 'marketplace' name is disambiguated from any competitor or counting concept.

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 when/when-not guidance with named alternatives: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use'; 'request_mcp asks us to build a NEW MCP when nothing fits.' It also gives explicit exclusions, e.g., 'without adding the MCP to the toolkit and without bloating the tool list,' making it clear when NOT to use install.

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 does not disclose any behavioral traits beyond the basic action. Moreover, the annotation idempotentHint=true contradicts the typical non-idempotent nature of reporting a bug, as each report likely creates a new entry. This contradiction merits a score of 1.

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 succinct, using two sentences without 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?

The description provides a clear purpose but lacks usage guidelines, preconditions, side effects, or any information about the expected behavior. It is not fully self-contained for an agent to use effectively.

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 description explains the 'conversation' parameter as needing recent messages for reproduction, but leaves 'context' and 'message' vague. Since the schema provides no descriptions, the description only partially compensates.

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: reporting bugs, missing features, or feedback. It is specific and distinct from sibling 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 implies usage (when you want to report an issue) but does not explicitly compare to alternatives or provide context on when to use it versus other tools. It lacks clear when-to-use 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 already state readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds that versions are current. No additional side effects, auth requirements, rate limits, or output shape are disclosed, but this is a low-risk read-only tool.

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, focused sentence with no filler, repetition, or unnecessary detail. It is easy to parse quickly.

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 this is a simple zero-parameter version-inspection tool with strong read-only annotations, the description is nearly complete. The only minor gap is the absence of output-shape detail or explicit guidance on how it relates to sibling informational tools.

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 empty input schema is fully self-explanatory and there is no parameter detail for the description to need to add. This matches the baseline for 0-parameter 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 clearly identifies the tool function using a specific verb and resource: showing current MCP platform and adapter versions. It does not explicitly differentiate from sibling tools like toolkit_info, which keeps it from a perfect score.

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 intended usage is implied: call when you need current version information. There is no explicit when-not-to-use guidance or mention of alternative information tools, but the tool is simple and parameterless.

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 description's implicit read-only nature aligns well. The description adds context by specifying exactly what is returned (installed MCPs, connection status, accounts, catalog tool counts), but it does not elaborate on performance, freshness, or any side effects, which is acceptable given the safety 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 sentence, tightly packed with all relevant details (what is returned and the components). No unnecessary fluff, and it is front-loaded with the main action. It earns full marks for 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?

Given the tool's simplicity (no parameters, no output schema, but a clear list of returned data), the description is sufficiently complete for an agent to understand the tool's purpose and expected output. It could optionally mention that the tool is useful for verifying connectivity, but that is not essential, so a 4 is appropriate.

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 has zero parameters, so the description does not need to document parameter semantics. The baseline for 0 parameters is a score of 4, and the description effectively conveys what the tool does without any parameter dependence, making it consistent.

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 specifies the verb 'Returns' and the resource 'current toolkit state', listing the specific data items (installed MCPs, connection status, accounts, catalog tool counts). It is distinct from sibling tools like 'show_version' or 'authenticate', and distinguishes itself as a read-only status/inventory tool.

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 this is for checking the toolkit's overall state, but it does not explicitly say when to use this versus other tools (e.g., when troubleshooting connections, before running a tool, or to see available accounts). No exclusions or alternatives are mentioned, so the guidance is minimal but not misleading.

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 meaningful behavioral context beyond the readOnly/idempotent hints: queries are hosted, require no platform credentials, are paid per query, and only access non-confidential citizen-available data. It also discloses LGPD data-controller responsibilities, though it omits details about return format or pagination.

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 well structured: three sentences, each adding distinct information about purpose, cost/access, and legal responsibility. It is front-loaded with the core purpose and contains no 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 11 optional parameters and no output schema, the description is not complete enough for reliable invocation. It explains cost and source but does not state which parameter combinations are valid, how results are returned, or whether pagination 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?

With 11 string parameters and 0% schema description coverage, the description provides no explanation of parameter meanings, combinations, or valid usage. The parameter names like cpf, cnpj, or processo are somewhat self-explanatory, but the description itself adds no semantic value beyond 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 identifies the tool as a query ('consulta') for TJSP first-instance judicial proceedings from an official source, with explicit mention of Brazilian official sources. This distinguishes it from the sibling tools, which are platform-level utilities like authentication or 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?

The description implies use when one needs official TJSP first-degree case information and provides operational context such as prepaid credit and no platform credentials. It does not explicitly state when-not-to-use or compare against alternatives, though no comparable sibling query tools exist.

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