TCU Jurisprudência

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

Beyond the idempotentHint annotation, the description adds meaningful behavioral context: session-only tokens expire versus permanent config tokens, and no-args invocation returns a login link. It does not disclose error cases or security storage details, but for an auth tool with sparse annotations, it provides valuable added transparency.

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 informative but somewhat run-on and informally structured, mixing context, configuration steps, and call instructions into a dense paragraph. It front-loads the main purpose and each sentence adds value, but it could be reorganized into clearer guidance for the two invocation modes.

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 one-parameter auth tool with no output schema, the description covers the key modes of use, the permanent versus session distinction, and the no-args behavior. It does not detail response shapes or errors, but the provided context is sufficient for an agent to select and invoke the tool correctly in common scenarios.

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 description coverage, so the description must compensate. It does so by explaining that the optional 'token' parameter expects a JWT pasted by the user, and that omitting it triggers the browser-link flow. This gives the parameter practical meaning beyond the bare string type in 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 states that the tool authenticates an MCP.AI connection for IDE agents via browser login and access token. It distinguishes the tool's purpose by explaining both the config-based and session-based authentication flows, though it does not explicitly contrast with the sibling '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 context: it explains the recommended permanent configuration approach, the alternative session-only token paste, and the no-args behavior to retrieve the login link. It lacks explicit when-not-to-use or alternatives compared to sibling tools like 'connect', but the guidance is actionable and specific.

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 safety. The description adds behavioral nuance by explaining the exact conditional output structure (authenticated:true and empty pending[] vs. connect_url and per-install URLs), which provides valuable context 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 extremely concise—just two sentences—front-loading the core purpose and then providing clear conditional details. Every sentence earns its place with no redundancy or filler.

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 params, no output schema), and the description covers the primary states (all connected vs. missing credentials) adequately. However, it does not explicitly address partial-connection scenarios or error conditions, leaving a small gap in completeness for an agent attempting to interpret the output.

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 schema coverage is trivially 100%. Per the baseline rule, a score of 4 is appropriate. The description does not need to explain parameters since there are none, and it does not add any parameter-related information beyond that.

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, and also describes the two possible outcomes based on connection state. It distinguishes itself from siblings like 'authenticate' by focusing on status checking 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 description implies when to use this tool (to check connection status) by describing its purpose and the conditions under which different results are returned. However, it does not explicitly mention alternatives or when not to use it, but given the sibling tools, the context is reasonably 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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true, etc.), the description discloses important behaviors: invoke runs one-off without installation, returns connect/checkout links for auth/payment, requires owner/admin for writes, and distinguishes installed_in_toolkit vs installed_in_workspace. It does not contradict annotations and adds substantial operational context.

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, covering many features in sequence. It starts with a strong summary but lacks bullet points or section breaks, making it somewhat hard to scan. However, the content is packed with useful information and not excessively verbose for the tool's complexity, so it's adequate 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 the tool's complexity (23 params, multiple actions, no output schema), the description provides a comprehensive overview: the core flow, auth requirements, one-off vs permanent behavior, payment handling, and the prompt library. It omits some actions like 'resume' and specific parameters, but covers the main use cases sufficiently. It could be more complete but is notably detailed.

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 23 parameters and 0% schema description coverage, the description must compensate. It explains the high-level action flow but does not define most parameters (e.g., limit, query, immediate, prompt_*). It mentions search/describe flagging installation status but not which parameter controls it. The description adds some meaning (e.g., 'action=search', 'tool_id') but leaves many parameters undocumented, so it partially compensates but insufficiently.

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: it is the official marketplace for discovering and running MCPs/tools, covering capability requests. It uses a specific verb-resource structure ('marketplace — the in-platform catalog... AND the way to run them') and explicitly outlines the core flow (search → describe → invoke), distinguishing it from sibling tools like report_bug or 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 provides explicit when-to-use guidance: it explains the core flow, advises 'prefer invoke for a single/occasional use' versus 'install only to make an MCP PERMANENT', and names alternatives like list_tools for current callables. It also covers subscribe/cancel for billing and request_mcp when nothing fits, giving clear context for choosing actions.

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 cover read/write and idempotency traits. The description adds the useful behavioral detail that the conversation array should be included for reproduction, but it does not disclose destination, acknowledgement, or duplicate-report behavior.

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, front-loaded sentence that wastes no words. It states the purpose and the key reproduction requirement in under 20 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?

The tool is simple and the annotations cover side-effect safety, but the description still leaves gaps: the context parameter is undocumented, no return/acknowledgement behavior is described, and there is no guidance around duplicate reports despite the idempotentHint.

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 purpose of the conversation parameter, but it does not explain the context parameter or explicitly map the message parameter to the bug/feedback content.

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 ('Report') and concrete targets ('a bug, missing feature, or send feedback'). This is unambiguous and clearly distinguishes the tool from sibling tools like authenticate, connect, and show_version.

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 explicitly indicates when to use the tool: for bug reports, missing-feature requests, or general feedback. It does not mention when not to use it or name alternatives, so it stops 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 the tool as read-only, idempotent, and non-destructive, so the description adds modest value by clarifying that it reports both platform and adapter versions. It does not describe the exact return format or any environment-related behavior, but for a simple version query 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?

The description is a single, front-loaded sentence that directly states the tool's purpose with no filler or repetition. 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?

Given the absence of parameters, minimal complexity, and rich annotations, the description is sufficiently complete for an agent to select and invoke the tool. It could mention the output shape or typical use case, but this is not necessary for such a straightforward version check.

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 burden for the description to carry. The schema coverage for parameters is complete, and the description correctly implies that no arguments 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 uses a specific verb ('Show') and a clear resource ('current MCP platform and adapter versions'). It is immediately clear what the tool reports, and it distinguishes itself from sibling tools that focus on authentication, marketplace, or searching.

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 usage context is implied: call this tool when version information about the MCP platform or adapter is needed. However, there is no explicit when-to-use guidance or mention of alternatives, though no sibling tool appears to compete directly with this function.

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, destructiveHint=false, and idempotentHint=true, which the description reinforces by mentioning 'dados abertos oficiais' and listing output fields, but it doesn't detail pagination limits or response specifics. The description adds scope ('recentes', 'sem palavra-chave') beyond annotations, so a 4 is appropriate given the strong annotation coverage.

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 fields, adds usage guidance, and names an alternative. No wasted 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?

For a list tool with 2 simple pagination parameters and no output schema, the description provides the essential information: what it lists, the fields returned, and the alternative for search. Given the annotations cover safety, it's complete for its purpose, though it could note that no keyword filtering is allowed (already implied by 'sem palavra-chave').

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 has 'inicio' and 'quantidade' with no descriptions, and schema description coverage is 0%, so the description carries no parameter details. However, the description implies pagination ('paginado'), which loosely maps to these parameters, but it doesn't explain how inicio/quantidade work or their defaults. Since these are common pagination parameters and the tool's purpose is clear, a baseline 3 is fair, though the description could compensate more.

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 lists recent TCU judgments (acórdãos) with specific fields (sumário, relator, colegiado, data da sessão, links), and distinguishes from tcu_buscar by noting it's without keyword search and paginated. The verb 'Lista' is specific and the resource is clear.

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 explicitly states when to use this tool (for listing recent acórdãos without keyword) and points to the alternative tcu_buscar for searching by topic, providing clear usage context and a named alternative.

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, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds behavioral detail about the output (title, summary, highlighted excerpts, links), which goes beyond the schema. It does not mention any potential side effects or limitations, but since annotations cover safety, this is sufficient. It adds value with return format details.

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 essential info: purpose, base options, and return fields. It is front-loaded with the action verb 'Busca'. Every clause adds value without redundancy. It's concise and 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?

Given the tool's moderate complexity (4 params, no nested objects), the description covers the core search capability, base choices, and return format. However, it omits how pagination parameters (inicio, tamanho) work)Skip, which might be needed for large result sets. It also doesn't mention any limitations like rate limits. Yet, for a read-only search tool, this is reasonably complete. Slight gaps on pagination keep it from a 5.

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% (no descriptions). The description explains 'base' with its enum options and implies 'termo' as the keyword. However, 'inicio' and 'tamanho' are not explained (likely pagination controls). This leaves two parameters ambiguous to the agent. The description compensates partially but not fully, so it is below average.

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 a textual keyword search over TCU jurisprudence, specifies the three base types, and details the return fields (title, summary, excerpts, etc.). This distinguishes it from the sibling tool tcu_acordaos_recentes (recent judgments) by emphasizing keyword search.

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 clear usage context by instructing the user to select a base and implies keyword search, but it does not explicitly state when to use this tool versus alternatives like tcu_acordaos_recentes. No exclusions or conditions are mentioned. This is clear context without exclusions, so a 4.

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 readOnlyHint, idempotentHint, and destructiveHint false, so the agent already knows it's a safe read. The description adds the specific content returned (accounts, catalog counts), which is helpful, but no further behavioral details (e.g., refresh behavior, latency) are given.

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, front-loaded sentence that lists all key contents without fluff. Very 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?

Given the tool's simplicity (no parameters, no output schema, high annotation coverage), the description is sufficient — it covers what the tool returns and implies its role in monitoring the toolkit, making it complete for an 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?

With zero parameters, the parameter burden is minimal. The description doesn't need to explain parameters, but it does enrich the tool's purpose by listing what the response contains, earning a solid baseline.

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 the current toolkit state, listing specific elements (installed MCPs, connection status, accounts, catalog tools) and distinguishes it from siblings that handle authentication, connection, marketplace, reporting, version, and searching.

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 implies usage for checking toolkit state and is different from siblings like connect or authenticate, but it doesn't explicitly state when not to use it or which alternative to choose, though context makes it clear enough.

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