Tribunal TJSC: Processo

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

Annotations indicate idempotentHint=true and destructiveHint=false, which the description does not contradict. The description adds behavioral context by explaining that calling with no args returns a login link, and that pasting a token provides session-only access. It also mentions the token is a JWT, which is useful. However, it doesn't disclose what happens after authentication (e.g., whether it modifies server state) beyond the idempotent hint.

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 but packs a lot of information: the target audience, the login process, the two usage modes, and the alternative permanent configuration. It is front-loaded with the purpose and provides actionable details. Slightly verbose but justified given the complexity of the authentication flow.

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 (authentication with two modes), the description covers the essential aspects: how to initiate login, how to use a token, and the alternative permanent setup. There is no output schema, so the description doesn't need to explain return values. It could mention what the response looks like (e.g., success/failure), but the core usage is well covered.

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 optional parameter 'token' with no description, and schema description coverage is 0%. The description compensates by explaining that the token is a JWT and how to use it: call with { token: "<jwt>" } after the user pastes, or with no args to get the link. This adds significant meaning beyond the bare 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: to authenticate an IDE agent by logging in via browser and obtaining an access token. It distinguishes itself from siblings by focusing on authentication, while siblings like connect and marketplace serve different functions. However, it could be more explicit about the resource being authenticated (the MCP server).

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: it explains when to use it (for login), how to use it (with a token or no args to get a link), and even offers an alternative (adding the token to the server's config for a permanent connection). This clearly differentiates between session-only and permanent authentication methods.

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 behavioral detail by specifying conditional response structures: authenticated:true with empty pending[] when all providers are connected, and connect_url plus per-install URLs when credentials are missing. This goes beyond annotation-only information.

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 compact and front-loaded with the core purpose ('Returns connection status and URLs'), followed by two conditional clarifications. Each sentence adds necessary information and there is no filler or repetition.

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 parameterless status tool with no output schema, the description fully covers the key states an agent needs to interpret results: full connection, pending providers, and missing-credential URLs. No critical behavior is omitted, and annotations confirm non-mutating, idempotent 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 tool has zero parameters and schema coverage is 100%, so the schema carries no parameter burden. With no parameters, baseline is 4, and the description does not claim any parameter behavior. It simply focuses on the return states, which 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 is specific: 'Returns connection status and URLs.' It clearly identifies the tool as a read-only status query and distinguishes it from sibling tools like authenticate by focusing on checking connection state 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?

Description explains the two concrete outcomes (all connected vs. missing credentials), giving context for when the tool is useful. It does not explicitly name alternatives or say when not to use it, but the context is clear enough for an agent to choose this for status checks.

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 important behavioral traits beyond annotations: that invoke runs a tool one-off without installing it, that missing credentials yield a connect link and empty wallet yields a checkout link, and that certain writes require workspace owner/admin. Annotations only say readOnlyHint=false and openWorldHint=true, so this adds substantial operational context. No contradictions 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 long but well-structured, starting with a clear definition, then the core flow, then edge-case behaviors, permissions, and prompt library. Each section adds value, and the length is justified by the tool's 23 parameters and multiple actions. Minor redundancies ('without adding... without bloating') slightly reduce conciseness.

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 is highly complete for a complex tool: it explains the primary purpose, the search→describe→invoke workflow, when to install vs invoke, authentication and payment fallback flows, workspace permissions, and the separate prompt library. Given no output schema, it describes return values for key actions (describe returns profile, publish_prompt returns shareable link, invoke returns connect/checkout links). The agent has all necessary information to select and invoke 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?

With 0% schema description coverage, the description carries the burden of explaining parameters. It gives rich meaning to the action parameter (listing all enum values and their purposes) and explains key parameters such as tool_id, mcp_id, and prompt_slug through the core flow and prompt library sections. However, many parameters (limit, query, immediate, tier_slug, cancel_reason, conversation, report_context, etc.) are left implicit, so it is not exhaustive.

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 a clear definition: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then details the core flow (search → describe → invoke), distinguishing it from sibling tools like authenticate or connect. The verb is explicit and the resource scope is 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 provides explicit when-to-use guidance for its main actions: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It also explains when to use request_mcp ('when nothing fits') and outlines the search→describe→invoke flow as the core path. This goes beyond mere context to give actionable decision rules.

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 indicate non-read-only, non-destructive, and idempotent behavior. The description adds one behavioral instruction—to include the conversation array for reproduction—but does not elaborate on side effects or outcomes beyond that.

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 efficiently conveys purpose and key instruction without any redundant words. It is well-structured and immediately understandable.

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 and lack of an output schema, the description adequately covers the necessary context, including the critical instruction to include conversation. It could be slightly more explicit about expected results, but overall it is complete for its purpose.

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 parameters with no descriptions. The description only clarifies the purpose of the 'conversation' parameter, leaving 'message' and 'context' unexplained. This provides partial semantic coverage, but significant gaps remain.

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: reporting bugs, missing features, or sending feedback. It is specific and distinct from sibling tools like authenticate or show_version, 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 implies usage for bug reports and feedback but does not explicitly state when to use this tool versus others. It lacks conditions or exclusions, providing only implicit guidance on when it should be invoked.

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, covering the safety profile. The description adds no additional behavioral context beyond that, but does not contradict 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, front-loaded with the purpose, and contains no filler. Every word is meaningful.

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 output schema, and annotations covering safety, the description is complete. It sufficiently conveys what the tool does without needing additional explanations.

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 provides no parameter details because none are needed; the schema is empty and fully covered.

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 MCP platform and adapter versions, with a specific verb and resource. No similar sibling tools exist, so it is unambiguous and 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 implies usage when version information is needed, but provides no explicit guidance about alternatives or exclusions. Given the simplicity of the tool, the implicit context is adequate, but not clearly stated.

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 safe no-side-effect nature is established. The description adds some value by specifying the informational content, but it does not disclose further behavioral details beyond what the annotations already cover; no contradiction exists.

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 core action and then packs in four meaningful pieces of information without waste. Every clause adds value, making the description both 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?

For a no-parameter, read-only introspection tool, this description is fully adequate. It states precisely what the output will contain, and the rich annotations cover side-effect and idempotency concerns. No output schema is necessary because the textual enumeration is clear enough for the 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 tool has zero parameters and 100% schema coverage, so there is no parameter semantics to explain. The baseline for a 0-parameter tool is 4, and the description appropriately focuses on return content rather than input 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 uses a specific verb ('Returns') and resource ('current toolkit state'), followed by a concrete enumeration of what is included: installed MCPs, connection status, accounts, and catalog tool counts. This clearly distinguishes it from sibling tools like connect or show_version, which address different concerns.

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 makes it clear to use this tool when one needs an overview of the toolkit's current state and connectivity. It does not explicitly name alternatives or exclusions, but its purpose is distinct enough from siblings like authenticate or report_bug, so the usage context is 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 the tool as read-only, idempotent, and non-destructive; the description complements this by adding details about the platform-hosted nature, lack of credentials, prepaid credit, and LGPD compliance. It does not contradict annotations and provides valuable context about the operational model and data responsibility.

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 dense paragraph that front-loads the core purpose but then packs in billing and legal disclaimers. While not overly long, the compliance and cost details could be condensed or moved to a separate field, so it earns an adequate but not exceptional score.

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 five optional parameters and no output schema, so the description needed to clarify selection logic and basic expectations. It fails to mention that at least one identifier is required or what kind of data is returned, leaving a significant gap for correct invocation despite the presence of annotations.

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 schema description coverage at 0%, the description was expected to explain how to use the five parameters (cpf, oab, cnpj, nome, numero_processo), but it does not mention any of them. The description neither clarifies which parameters are needed nor whether at least one is required, leaving the agent to guess—failing to compensate for the lack of schema documentation.

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: 'Processo, consulta em fonte oficial' (Process query from official source), identifying the resource (judicial processes from TJSC) and the action (consulta/query). It distinguishes itself from siblings by specifying the tribunal and source, leaving no ambiguity about what it 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 notes that no platform credentials are required and that it is pay-per-query, which offers some context, but it fails to specify when to use this tool versus alternatives or when not to use it. There is no mention of prerequisites, required parameter combinations, or comparisons with sibling tools like 'connect' or 'marketplace'.

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