Tribunal TRT23: Certidão Eletrônica de Ações Trabalhistas (CEAT)

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

Annotations already indicate readOnlyHint false and idempotentHint true, so the description does not need to repeat those. It adds process context (browser login, config header) but does not detail side effects (e.g., whether a session is stored server-side, or what happens on successful auth). It explains the flow but not the state changes or response structure, leaving room for ambiguity.

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 core purpose and then quickly detailing the two invocation paths. Every phrase adds value—nothing is redundant or padded. It is well-structured for quick parsing by an agent.

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 authentication tool with one optional parameter and no output schema, the description covers the invocation modes, configuration option, and token format. It lacks details on error handling or response content, but given the tool's simplicity and the annotations, the description is reasonably complete. The guidance on permanent vs session setup adds practical 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 0% schema description coverage, the description carries the burden of explaining the 'token' parameter. It clearly states that token is a JWT passed after the user pastes it, and that no arguments yields a login link. This adds meaningful semantics beyond the bare schema (which only lists a string property), compensating well 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: authenticate an IDE agent by logging in via browser and obtaining an access token. It specifies two distinct usage modes (config header for permanent access, or passing a token for session login), making its function unambiguous even among siblings like '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?

It provides explicit instructions on when to use each method: permanent config vs session-based token. The description tells the agent how to call the tool (with or without token) and what the user should do. However, it does not explicitly contrast with alternatives like 'connect' or state when not to use this tool, so it lacks direct exclusion 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 mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful state-dependent behavior (authenticated:true when connected, connect_url when credentials missing), which complements the annotations. However, it does not mention partial connection states, leaving a minor transparency gap.

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-loads the primary purpose, and every sentence adds value by explaining state-dependent outputs. No filler 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 status tool, the description covers the main return states (all connected vs missing credentials) and URL types. However, it omits partial connection scenarios, which could be a realistic use case. Overall, it is fairly complete given the tool's simplicity.

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 description needs no parameter explanations. The baseline for zero parameters is 4, and the description provides no unnecessary parameter details, 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?

The description clearly states the tool returns connection status and URLs, with specific conditional outcomes. This distinguishes it from siblings like authenticate, which initiates connections, making the purpose unmistakable.

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 checking connection status but does not explicitly state when to use connect vs authenticate or other alternatives. The conditional behavior (all providers vs missing credentials) gives context but no direct guidance on alternative selection.

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 only provide readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds critical behavioral context: writes require workspace owner/admin, invoke runs one-off without installing, invoke returns connect/checkout links when needed, search/describe flag installed states, and the prompt library is separate. This provides a comprehensive picture of side effects, permissions, and operational nuances beyond 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 a single dense paragraph but logically structured: opens with purpose, then core flow, then key distinctions (invoke vs install), then other actions, then prompt library. Every sentence adds value—no filler or repetition. It is long due to inherent complexity (14 actions, permissions, billing), but it is tightly packed and front-loaded with the primary purpose. This is concise for the scope.

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 (23 params, no output schema, minimal annotations), the description covers the essential aspects comprehensively: the core search→describe→invoke pipeline, when to use invoke vs install, auth and payment flows, permission requirements, actions for billing/reporting/requests, and the separate prompt library. It explains practical usage scenarios and edge cases (retry after payment) that agents need. Missing minor details like 'resume' or 'immediate' do not detract from overall usability.

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 23 parameters with 0% coverage in the description. The description compensates by explaining the core flow and mapping key parameters: 'action=search', 'describe returns one MCP's full profile', 'tool_id' and 'arguments' for invoke, and prompt-related parameters for the prompt library. However, it does not explain every parameter (e.g., limit, immediate, conversation, cancel_reason details) or their exact formats, leaving some gaps. Since coverage is 0%, it does a good job but not exhaustive, so a 4 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?

The description opens with 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly identifies the tool as a marketplace and catalog for MCPs, with specific verbs like 'search', 'describe', 'invoke', and 'install'. It distinguishes itself from sibling tools (e.g., authenticate, connect) by focusing on MCP discovery and execution, making the purpose unambiguous and unique.

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 states when to use which action: 'prefer invoke for a single/occasional use'; 'Use install only to make an MCP PERMANENT in the active toolkit'; 'subscribe/cancel handle per-MCP billing'; 'report_bug sends feedback'; 'request_mcp asks us to build a NEW MCP when nothing fits.' It also contrasts invoke vs install and mentions auth and billing side effects (connect link, checkout link) and when to retry. This gives clear decision 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 declare the tool as non-read-only, idempotent, and non-destructive. The description adds a useful reproduction detail (conversation array) but does not disclose additional side effects, authentication needs, or post-submission behavior. 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 two short sentences, front-loads the core purpose, and includes an actionable instruction with no filler or redundant 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?

For a low-complexity tool with three string parameters, no output schema, and annotations covering basic safety, the description covers the main purpose and a key usage nuance. However, it does not explain expected return behavior or fully document all parameters, making it minimally adequate rather than complete.

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. It clarifies the conversation parameter's purpose ('recent messages for reproduction') but provides no semantics for context and no explicit explanation of the required message field, leaving key gaps for an agent.

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 ('bug, missing feature, or feedback'), making its purpose immediately clear and distinguishing it from sibling tools like connect 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?

It clearly states the scenarios for use (bug, missing feature, feedback) and includes an instruction to provide the conversation array for reproduction. It does not explicitly mention exclusions or alternative tools, but the context is evident enough for basic 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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which cover the safety profile. The description adds a small behavioral detail by specifying that both platform and adapter versions are returned, but it does not disclose any other behavioral traits such as output format or latency. With annotations present, this is adequate.

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 clear sentence with no unnecessary words, front-loading the action and object effectively.

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, read-only version-checking tool, the description fully conveys the purpose and what information is returned. No output schema is present, but the description explicitly names the two version categories, making it complete enough for agent use.

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 coverage is trivially 100%. The description does not need to explain any parameters. Following the baseline for 0 params, a score of 4 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?

The description clearly states 'Show the current MCP platform and adapter versions' with a specific verb (show) and resource (MCP platform and adapter versions). This distinguishes it from sibling tools like authenticate, connect, and marketplace, 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?

The tool's use case is immediately clear as a version query, and no alternative sibling provides version information. However, there is no explicit when-to-use or when-not-to-use guidance, so it falls short of a 5.

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 this as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds useful behavioral context by specifying exactly what data will be reported, which is especially valuable given there is no output schema.

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, information-dense sentence that is front-loaded with the main purpose and then enumerates the returned data. No filler or redundant wording.

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 informational tool, the description is complete: it states what the tool returns and covers the key categories of data. The lack of an output schema is mitigated by the explicit enumeration of returned contents.

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 description correctly focuses on return content rather than parameter behavior. The baseline for no parameters is 4, which is appropriate here.

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 names a clear resource ('current toolkit state'), then itemizes the exact content: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from siblings like show_version 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 this is the tool to call when you need an overview of the toolkit's current state, but it does not explicitly state when to use it or compare it with alternatives such as show_version or marketplace. The usage context is recognizable but not formally articulated.

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?

Adds transparency about data sensitivity (not confidential), LGPD compliance, and payment model, which complements the readOnlyHint 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?

Description is concise, covering key points without unnecessary detail, though includes legal boilerplate.

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?

Lacks output description, parameter requirements, and potential error cases; only states what it queries, so incomplete.

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?

Input schema has three parameters (cpf, cnpj, nome) but description gives no hints on their usage, leaving ambiguity.

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 queries CEAT (labor actions certificate) from official source, with specific verb 'consultar' and resource 'CEAT', distinguishing it from generic 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?

Provides usage context: no platform credentials required, pay-per-query with prepaid credits. However, it doesn't explicitly state when to use vs not, but given no similar siblings, this is adequate.

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