Tribunal TJMS: Conferência de Certidão

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

The description adds significant behavioral context beyond annotations—explaining the default browser login flow, the permanent vs session distinction, and the behavior with/without args. It does not contradict the annotations (e.g., idempotentHint=true), and even though annotations exist, the description enriches understanding of the tool's side effects and configuration.

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 information-dense and front-loaded with the primary purpose, then efficiently explains two usage branches. While a bit long and run-on, every sentence contributes necessary guidance without 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?

For a moderately complex authentication flow, the description covers essential behaviors: how to authenticate permanently, how to do a session login, and what happens with no arguments. It does not specify return values or error handling, but that is acceptable given no output schema and the description's focus on the primary usage.

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 Decryption for the optional 'token' parameter is excellent. The description explicitly explains that providing a token ('{ token: "<jwt>" }') performs a session-only login, while calling with no args returns the login link. This fully compensates for the lack of schema-level descriptions.

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 authenticates to MCP.AI for IDE agents (Cursor, etc.) with a specific verb ('log in') and resource, and explains the underlying flow. However, it does not explicitly contrast with sibling tools like 'connect', so it misses the differentiator for a perfect score.

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 context on when to use the tool and even distinguishes permanent (server config) vs session-only login paths. However, it does not mention when NOT to use this tool or suggest alternatives, so it lacks explicit exclusions.

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 idempotentHint=true, indicating a safe, read-only operation. The description adds valuable behavioral context by detailing the two return states (all connected vs. missing credentials) and explaining that missing credentials yields both a toolkit-level connect_url and per-install URLs, which is not evident from annotations alone.

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 with front-loaded purpose ('Returns connection status and URLs') and no redundancy. Each sentence carries critical information about conditional behavior, making it efficient 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 simple status-check tool with no parameters and no output schema, the description covers the essential scenarios (all connected and missing credentials) and leverages annotations for safety. It could explicitly mention partial connectivity states, but the given description is sufficiently complete for basic usage.

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 no parameters (schema properties are empty), so there is nothing for the description to explain. Per the rubric, a baseline of 4 is appropriate for 0-parameter tools, and the description correctly avoids inventing 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 the tool returns connection status and URLs, with specific conditions for when authenticated:true and empty pending[] are returned versus when connect_url and per-install URLs are provided. This distinguishes it from sibling tools like authenticate, which would handle the actual authentication flow.

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 and hints that missing credentials should prompt authentication via connect_url, but it does not explicitly mention when to use this tool versus siblings like authenticate or provide exclusions. The conditional outputs give context but not direct alternative 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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description adds key behavioral details: invoke works without installation, returns connect/checkout links when credentials/payment are needed, and writes require workspace owner/admin. This gives the agent a clear safety and side-effect profile without contradicting 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 lengthy but justified given the tool's complexity. It front-loads the purpose, then explains the flow, key behaviors, and prompt library. Each sentence adds value (e.g., auth requirements, link handling, install vs invoke). Slight redundancy could be trimmed, but overall it is well-structured for the breadth of functionality.

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 tool with 23 parameters, no output schema, and a dual role (MCP execution + prompt library), the description covers the essential context: discovery and execution flow, install/one-off behavior, credential/payment handling, and permission requirements. It omits error handling and detailed return formats, but given the annotations and the description's depth, it is reasonably 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?

The description explains the central 'action' parameter and the flow's key parameters (query, mcp_id, tool_id, arguments) but leaves many of the 23 parameters undocumented (limit, immediate, tier_slug, prompt_* variants, cancel_reason, etc.). With 0% schema coverage, the description carries a heavy burden and only partially compensates by explaining the main workflow, not individual param formats or defaults.

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 is the official marketplace for MCPs/tools and covers discovery, execution, installation, and prompt library management. It explicitly lists the core flow (search → describe → invoke) and differentiates from sibling tools by positioning itself as the central catalog and execution hub. The verb 'marketplace' plus detailed action breakdown makes 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?

Provides explicit guidance on when to use invoke vs install ('prefer invoke for a single/occasional use', 'use install only to make an MCP PERMANENT'), and outlines the core flow search→describe→invoke. It also mentions subscribe/cancel for billing and request_mcp when nothing fits. However, it does not explicitly contrast with sibling tools like authenticate or connect, leaving some ambiguity about alternative tools.

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 idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by instructing users to include the conversation array for reproduction, which is behavioral context beyond 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 sentences, front-loaded with purpose, no redundant 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?

For a simple feedback tool with no output schema, the description covers the core purpose and the key reproduction requirement. It lacks explicit guidance on what message should contain, but given the tool's simplicity, it is largely 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 explain parameters. It only mentions the conversation array, leaving 'message' (required) and 'context' unaddressed. This is insufficient for a required field and an optional context parameter.

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 feedback. It uses a specific verb ('report') and resource (bug/feature/feedback), and is distinct from unrelated sibling tools.

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 specifies when to use the tool (to report bugs or feedback) and provides a key usage hint about including conversation history. It does not explicitly list alternatives or exclusions, but siblings are unrelated, so 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read. The description adds minimal information beyond the annotations ('current' is mildly useful, implying runtime state retrieval), but it does not elaborate on what 'versions' encompasses or whether network/service calls are involved. Given annotation coverage is strong, the description meets a minimum bar but does not deeply enrich understanding.

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 sentence, zero waste. 'Show the current MCP platform and adapter versions.' – front-loads the verb, states exactly what is displayed, and includes the word 'current' to signal runtime retrieval. The scarce description matches the tool's trivial nature.

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 strong annotations (readOnly, idempotent) and a trivial purpose, the description is complete. It does not explain the output format, which could matter if the agent needs to parse versions, but given the simplicity and the lack of an output schema, the tool appears to be a diagnostics utility where full detail is unnecessary. Could mention if it performs network calls for an up-to-date version check vs. local, but this is a minor gap.

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 burden on the description. The schema is trivially satisfied at 100% coverage, and description correctly focuses on the return value (the version info) rather than inventing parameter details. A 4 is appropriate given the natural baseline for a zero-parameter informational tool.

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' with a clear object 'current MCP platform and adapter versions', precisely indicating what the tool does. It clearly distinguishes itself by referring to 'MCP platform and adapter', which is distinct from sibling tools targeting connectivity ('connect'), auth ('authenticate'), or reporting ('report_bug').

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 is simple and its usage is effectively implied by its name and description; however, there is no explicit 'when to use' or 'when not to use' guidance nor mention of alternatives. Since the tool is trivial (zero parameters), the absence of heavy guidance is acceptable, though a sentence reinforcing it as a read-only informational call would move it to 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context by specifying what 'state' means in terms of returned data: installed MCPs, connection status, accounts, and catalog tool counts. No further side effects are implied, and 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?

A single, well-structured sentence that front-loads the verb and resource, then efficiently lists the four output dimensions. Every phrase earns its place with 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 there are no parameters and no output schema, the description fully covers what the agent needs to understand the tool's return value: installed MCPs, their connection status, connected accounts, and catalog tool counts. This is complete for a no-input informational 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?

With zero parameters, the schema carries no burden and the baseline is 4. The description sufficiently conveys that the tool takes no inputs and simply returns the current state, so no parameter documentation 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 opens with a specific verb and resource: 'Returns the current toolkit state', then enumerates exactly what is included (installed MCPs, connection status, connected accounts, catalog tool counts). This clearly distinguishes it from siblings like show_version, which reports version info rather than the overall toolkit 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 makes the use context clear: call this to inspect the toolkit state, including MCP installations and connections. It does not explicitly state when not to use it or name alternatives, but the scope is unambiguous enough for an agent to select it appropriately among the sibling tools.

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 adds meaningful context beyond the readOnlyHint annotation by clarifying the nature of the data (public, not confidential), the payment model, and the client's LGPD responsibilities. This reassures the agent of safety and legality. It doesn't contradict the readOnlyHint or idempotentHint 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, dense paragraph packed with useful information: purpose, hosting, payment model, data source, legal basis, and compliance note. Every sentence contributes value. It is front-loaded with the most critical information.

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 simple parameter set (4 scalars, no enums) and no output schema, the description covers the operational context well by explaining the payment model and the data's public nature. It could improve by hinting at response format or error conditions, but it is complete for a straightforward query 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?

Schema description coverage is 0%, so the description should compensate, but it doesn't explain any of the four parameters. However, the parameters themselves (cpf, cnpj, data_pedido, numero_pedido) are self-explanatory from their names, and the schema enforces the required ones. This is a case where the schema structure does most of the work, but the description could still add value by indicating, for example, that cpf/cnpj are mutually exclusive.

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 specifies the tool's purpose (Conferência de Certidão, consulta em fonte oficial) and names the resource (Tribunal TJMS). It could be clearer by matching the exact tool name, but it effectively communicates a verification query for official court records. It doesn't explicitly distinguish from sibling tools, which are unrelated.

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 indicates this is a pay-per-query service against official Brazilian sources, implying when to use it (need for official certificate validation). It does not explicitly list alternatives, but the unique context of pre-paid credits serves as a clear usage signal. It lacks explicit when-not-to-use guidance, which is the only gap.

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