Tribunal TRT6: Certidão Eletrônica de Ações Trabalhistas (CEAT)

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

With annotations indicating readOnlyHint=false and idempotentHint=true, the description adds context about outcomes (permanent vs. session-only) and the flow (browser login, token copy). It does not contradict annotations and provides useful behavioral details beyond the minimal structured data.

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 three sentences with no redundancies, front-loading the core action ('log in in the browser, copy the access token') and then providing precise alternatives. Every sentence adds value, making it appropriately sized 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?

Given the tool's simplicity (one optional param, no output schema), the description covers all necessary information: how to invoke with and without a token, the two authentication modes, and their implications. It is complete for an IDE agent to use correctly without further guidance.

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 only an optional 'token' parameter with zero schema description coverage. The description fully explains it: passing a JWT for session login, and omitting it to obtain a link. This compensates completely for the lack of schema metadata, giving clear 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 purpose: authenticating IDE agents by logging in via browser and obtaining an access token. It distinguishes itself from siblings by specifying 'MCP.AI for IDE agents' and detailing the authentication flow, making it distinct from a generic 'connect' 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 provides clear usage guidance by outlining two modes: permanent configuration via a header and session-only login via a token. It explains when to use each, but does not explicitly mention alternatives or when not to use this tool, though the context is well implied.

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?

With annotations already declaring readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the tool's safety profile is clear. The description adds context about what the status means (authenticated:true, pending[]), which is useful. However, it doesn't clarify potential rate limiting or whether it makes external calls, but the read-only nature is well covered.

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 (two sentences) and directly front-loads the core purpose. It includes necessary details about two key states without extra fluff. Every sentence contributes to understanding the tool, making it highly 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?

The tool is simple (no parameters, no output schema), and the description covers the main behavioral states (authenticated, pending, and connect URLs). It is complete enough for an agent to know what to expect. Minor detail about the exact format of URLs is omitted, but that's not critical for a status check tool.

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 there is no parameter semantics to explain. The baseline for tools with no parameters is 4, and there are no gaps in the schema description coverage. The description's focus on output states compensates for the lack of parameter details.

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 what the tool does: it returns connection status and URLs, including authenticated state and pending connections. It also explains the two possible states (all connected vs. missing credentials), making its purpose unambiguous. This distinguishes it from sibling tools like 'authenticate' and '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 the tool is used to check connection status, but it does not explicitly say when to use it versus alternatives like 'authenticate' (likely for initiating connections). It also doesn't mention when not to use it. However, the detailed state descriptions provide clear context for when it would be relevant.

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?

Despite annotations being thin (only title/readOnlyHint=false/openWorldHint=true), the description carries extensive disclosure: invoke runs one-off without installing or bloating the list, returns connect link when auth needed, checkout link when wallet empty (then retry), permission requirements for writes, and per-MCP billing semantics. All of this is beyond what annotations provide, and nothing contradicts readOnlyHint=false since writes are disclosed.

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 wall of text with no paragraph breaks or structure, making it hard to scan despite containing high-value content. Every sentence does earn its place — there's little fluff — but the lack of structural organization (flows, prompts library, permissions are all jammed together) hurts readability. This is informative density, not concise 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?

For a 23-parameter, 14-action tool with no output schema and 0% schema coverage, this description is remarkably complete: it explains the orchestration flow, the one-off execution model, auth/payment edge cases, permission rules, and the separate prompt library subsystem. Minor gaps: 'resume' action is never mentioned, and return-value formats are only implied (profile, connect link, checkout link) rather than specified.

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 coverage is 0%, so the description must compensate — and it largely does. The description narrates nearly every action enum value (search, describe, install, uninstall, subscribe, cancel, invoke, report_bug, request_mcp, list_tools, search_prompts, get_prompt, publish_prompt), plus key params like tool_id and arguments implied by the invoke flow. Only 'resume' goes unaddressed, and generic params (limit, query, message, prompt_*) lack explicit semantics, relying on inference from action names.

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 states a specific, rich purpose: the official mcp.ai marketplace catalog AND runtime. It clearly distinguishes from siblings (authenticate, connect, show_version, etc.) by positioning itself as the catalog/search/discovery/execution hub, and names the core flow (search → describe → invoke). The dual catalog-and-executor framing is precise and unique among siblings.

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?

Gives explicit when-to-use guidance: prefer invoke for single/occasional use, use install only for permanent toolkit membership, search for discovery, describe for profile, list_tools for what's callable now. It also names explicit exclusions (writes require owner/admin) and alternative paths (request_mcp when nothing fits). This is textbook usage 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 idempotentHint=true and destructiveHint=false, so the tool is implied safe. The description adds value by explaining that including the conversation array helps reproduction, which gives context on side effects (none destructive). It does not exceed the annotation baseline significantly, but provides a small extra behavioral insight.

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 only two sentences, with no filler words. Every word serves a purpose, and the most actionable guidance (including the conversation array) is stated upfront. It is concise without losing necessary 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 no nested objects, no output schema, and a single required parameter, the description covers the key aspect (reproduction through conversation). It does not describe return values, but that is not expected given the lack of output schema. Minor gaps like what happens after submitting are absent, but they are not critical for this 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?

With 0% schema description coverage, the description must carry parameter documentation. It explicitly mentions the 'conversation array' (mapping to the 'conversation' param) and implies it should contain recent messages, but it does not explain 'context' or 'message'. The description partially covers the parameters but leaves two of the three undocumented, so it underperforms for a zero-coverage 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 uses a clear verb+resource pattern ('Report a bug, missing feature, or send feedback') and distinguishes the tool from siblings like 'connect' or 'marketplace'. It lacks a definitive scope statement, but the purpose is immediately understandable and non-tautological.

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 the tool should be used when the user wants to report issues or provide feedback, and instructs to include the conversation array for reproduction. However, it does not explicitly state when not to use it or name alternatives, though the instruction is clear enough for common 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no extra behavioral context (e.g., that it just prints versions), but it doesn't contradict annotations. Since annotations cover the safety profile, this is acceptable.

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?

One concise sentence, perfectly sized for a trivial 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?

For a zero-parameter informational tool with safety annotations, the description is sufficient to convey purpose and 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?

No parameters exist; baseline is 4. Schema is empty with 100% coverage, so description adds nothing 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?

Clear verb ('Show') and explicit resource ('MCP platform and adapter versions'). Distinct from sibling tools like authenticate or connect, making its purpose 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?

For a trivial read-only utility, the description clearly implies when to use it (to check versions) without needing explicit alternatives or exclusions. The tool is self-explanatory given its name and simple purpose.

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 covered. The description adds value by specifying the exact information returned (installed MCPs, connection status, accounts, catalog tool counts), giving the agent a precise expectation of the output without contradicting 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?

A single, information-dense sentence that front-loads the action and resource, then lists components in a structured manner. There is 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?

Given the tool's low complexity (no params, no output schema), the description fully covers the return values by naming all components. No further details are necessary for an agent to invoke or interpret the result.

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 input schema is trivially 100% covered. Per calibration, 0 params warrant a baseline of 4. The description adds no parameter info (none needed), but it appropriately focuses on the return contents.

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 identifies the resource ('current toolkit state'), then enumerates the exact contents (installed MCPs, connection status, accounts, catalog tool counts). This clearly distinguishes it from sibling tools like authenticate or connect, which perform actions rather than report state.

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 as a read-only inspection tool. It doesn't explicitly state when to use vs alternatives, but the context (checking toolkit state) is clear and siblings are all distinct actions, so no exclusions are needed. There is no explicit 'use this when...' guidance, but the purpose is self-evident.

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. Beyond that, the description adds that no platform credentials are needed, queries are billed via prepaid credit, data is not confidential, and the client is the data controller under LGPD. These are useful behavioral details not present in annotations, though some regulatory text is verbose.

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 (3 sentences) but packs in legal and billing disclaimers that could be moved elsewhere. It lacks a clear front-loaded summary of functionality, instead mixing purpose with compliance notes. It is not wasteful, but could be better organized.

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 3 optional parameters, no required fields, and no output schema, the description leaves out crucial usage details like mutability of parameters and what the response contains. It does not clarify how parameters combine or whether at least one is needed. The lack of output schema documentation further reduces 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?

Schema description coverage is 0%; the description does not mention cpf, cnpj, or nome at all. It doesn't explain parameter formats, optionality, or that at least one may be required. Since the description carries full burden and provides zero information about parameters, this is a critical gap.

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 consultation for TRT6 CEAT (labor lawsuit certificate) from an official source. While it doesn't explicitly list parameters, 'consulta' and 'informação' make the purpose clear. It differentiates from siblings (which are generic platform tools) by naming the specific court and certificate type.

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 mentions cost (pay-per-query), hosting, and LGPD responsibilities but does not state when to use this tool versus alternatives, nor does it provide conditions or exclusions. It implies usage for querying official Brazilian data but gives no explicit guidance on when to choose this tool or what prerequisites exist (e.g., at least one parameter).

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