Tribunal TJSP: Consulta Processual Unificada (Eproc)

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

Annotations declare idempotentHint=true and readOnlyHint=false; the description enriches this by detailing JWT format, non-expiring vs. session-only semantics, the exact Authorization Bearer header format, and browser-flow behavior—none of which appear in the structured fields. This materially improves an agent's ability to invoke correctly.

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?

A single well-packed paragraph where each clause earns its place—no filler. Slight deduction for dense, meandering sentence structure that could be broken into two or three sentences for scannability, but overall efficient.

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 single-optional-param tool with no output schema and no nested objects, the description is complete: it covers the primary use case, an alternative permanent auth path, argument format, and default behavior. No critical operating detail is left unspecified.

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 burden falls entirely on the description. It fully compensates by explaining the optional 'token' parameter as a pasted JWT for session login and clarifying the no-args call returns the auth link. This transforms the bare schema string into an actionable contract.

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 specific verbs (log in, copy access token, paste) and clearly identifies the resource (MCP.AI for IDE agents). It distinguishes itself from sibling 'connect' by focusing on credential exchange and session management, making the auth-specific 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?

Explicitly contrasts two usage modes—permanent config-based login via header versus session-only pasted token—and specifies no-args behavior for the link. It stops short of explicitly naming alternatives or stating 'don't use this if…', but the guides are actionable and contextually clear.

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 and destructiveHint=false. The description adds valuable conditional behavior: 'authenticated:true and empty pending[]' when connected, and 'connect_url' when credentials are missing. This complements the annotations without 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 two sentences, highly concise, and front-loaded with the core purpose. The conditional details are presented efficiently without unnecessary 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?

This is a simple zero-parameter, read-only status tool. Annotations cover safety, and the description explains the two relevant output states. No output schema exists, but the description sufficiently covers return values. No 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?

The tool has zero parameters and the input schema is empty, so schema coverage is 100%. With no params, the baseline is 4; the description correctly focuses on output rather than param details, and no parameter info 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 'Returns connection status and URLs' with a specific verb and resource. It distinguishes itself from siblings like authenticate by focusing on status retrieval rather than initiating 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 context implies use for checking connection status, especially given the sibling 'authenticate', but the description does not explicitly state when to use this tool over alternatives or provide exclusions. It only describes behavior, not usage scenarios.

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 discloses rich behavior beyond the annotations: invoke works even when the MCP is not installed (one-off, no toolkit bloat), returns connect links for auth needs and checkout links for empty wallets with a retry flow, and writes require workspace owner/admin. Search/describe flag installed status. The readOnlyHint=false annotation aligns with the documented mutating actions - 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 a dense, run-on wall of text with no bullets, section breaks, or paragraph separation between the core marketplace behavior and the prompt library subsection. Every sentence carries useful information, so nothing is wasted, but scanability suffers badly for a tool with 14 action modes; the structure does not match the tool's complexity.

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?

Despite having no output schema and a massive scope (14 actions, 23 params, 0% param coverage), the description covers the end-to-end flows: search→describe→invoke, connect/checkout link returns with retry, install-vs-invoke permanence, admin requirements, and what describe/invoke/publish return (profile with tool_id+params+pricing+auth, links, shareable slug). Only a clear output/return structure is missing, which the prose partially mitigates.

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 across 23 parameters, the description carries the full burden and substantially compensates: it explains the action enum (all 14 values), the tool_id+arguments relationship for invoke, mcp_id for describe/install, and the prompt library params (prompt_slug, prompt_body, prompt_vars, prompt_title, prompt_targets, prompt_category, prompt_description). However, several params (limit, query, message, conversation, immediate, tier_slug, cancel_reason/comment, report_context, request_name/details) are only implied or omitted, so it doesn't fully cover all 23.

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 this is the official mcp.ai marketplace - the in-platform catalog plus the way to run them, covering capability requests. It precisely defines the dispatch role via the action parameter (search/describe/invoke/install/etc.), which distinguishes it from single-purpose siblings like authenticate, connect, and toolkit_info. The verb+resource+scope is specific and 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?

Explicit when-to-use guidance throughout: the core flow is spelled out (search discovers → describe returns profile → invoke runs), with direct preference statements like 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also covers when to use list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library actions, plus owner/admin requirements for writes and the retry-after-link flow.

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 declare idempotentHint=true and readOnlyHint=false, and the description adds the instruction to include conversation for reproduction. It does not describe side effects or post-report actions, but it does not contradict 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 concise, front-loaded sentences with no extraneous information. 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?

The description covers the core purpose and one parameter but misses context and message semantics. Given the tool's simplicity, it is adequate but not fully complete for a 3-parameter tool with no 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 description explains the conversation parameter but not message or context. Since the schema has no descriptions (0% coverage), the description partially compensates but leaves ambiguity for context and message semantics.

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 sending feedback. This is a specific verb+resource and distinguishes it from sibling tools (auth, version, toolkit info).

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 when to use it (when you need to report an issue) and is distinct from siblings. However, it doesn't explicitly mention when not to use it or provide alternative tools, but given the sibling set, this 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?

Annotations already declare readOnly, idempotent, non-destructive. Description adds what it shows (platform and adapter versions) but doesn't detail output format or side effects beyond that. It's consistent with annotations, 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?

Single sentence, precise, front-loaded, 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?

Simple zero-param read-only tool, description adequately states purpose. Could mention output format, but not necessary.

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, so schema coverage is complete. Description doesn't add param info, but per instructions baseline 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 states a specific verb ('Show') and resource ('current MCP platform and adapter versions'). It clearly defines the tool's purpose and distinguishes it from sibling tools like authenticate, connect, etc., 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?

Usage is implied: use when you need version info. No explicit exclusions or alternatives are mentioned, but given the trivial nature and distinct purpose, it's 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, so the safety profile is well-covered. The description adds specific behavioral context by listing exactly what information is returned, which is valuable beyond 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 a single sentence that front-loads the purpose and lists the specific data returned. Every word contributes value, with no fluff 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?

For a zero-parameter read-only tool, the description fully enumerates the components of the return value (installed MCPs, connection status, accounts, catalog tools count). Since there is no output schema, this description provides sufficient completeness for an agent to understand what it will receive.

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 no parameters, the baseline is 4. The description correctly avoids redundant parameter explanations since there are none, and no additional semantics are 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 states a specific verb ('Returns') and resource ('current toolkit state') with detailed content: installed MCPs, connection status, accounts, and catalog tool counts. It clearly distinguishes from siblings like authenticate or connect, which serve 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?

The description implies its usage as the go-to tool for inspecting toolkit state, which is clear from the content it returns. However, it does not explicitly mention when not to use it or compare it to alternatives, but given the unique purpose among siblings, this is a minor gap.

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 need not repeat those. It adds valuable extra behavioral context: it is hosted by the platform, requires no platform credentials, and is paid per query via prepaid credit. It also clarifies data privacy and LGPD compliance. These disclosures go beyond the structured annotations and are useful for agents deciding on usage.

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 moderately concise but includes extraneous content about payment and LGPD that, while relevant, could be streamlined. It front-loads the main purpose but then spends several clauses on operational and legal caveats. The structure is acceptable but not tight; some sentences could be merged or removed without losing essential meaning.

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 read-only query with one parameter and no output schema, the description conveys the tool's purpose and some operational context (payment, no credentials). However, it does not describe what the tool returns (e.g., process details, parties, status) or any limitations (e.g., only public cases). Given the absence of an output schema, this gap leaves the agent uncertain about the data structure, reducing 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?

The schema has one required parameter 'numero_processo' with no description (coverage 0%). The tool description does not elaborate on this parameter: it does not specify the expected format (e.g., CNJ standard), constraints, or examples. While the name suggests a process number, an agent may not know the exact legal format required for successful invocation. The description fails to compensate for the schema's minimal information.

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: 'Consulta Processual Unificada (Eproc)' at TJSP, a court process query. It explicitly names the resource (TJSP unified process) and the action (consult). It also distinguishes itself from sibling tools, which are generic platform operations (auth, connect, marketplace, etc.), by specifying the legal/process domain.

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 is for querying official TJSP process information, but it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or preconditions beyond payment and data responsibility. There is no mention of when not to use it. The usage context is implied by the purpose, but not explicitly guided.

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