Tribunal TJSP: Colégio Recursal e Turma de Uniformização

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

Beyond the annotations (idempotentHint, destructiveHint), the description discloses important behavior: token in config is permanent and non-expiring, while pasted token is session-only. It also explains the no-args behavior, which is helpful for the agent.

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 somewhat wordy but well-structured: it starts with context, then gives two options (config vs token) and the no-args case. Each sentence adds value, though it could be tightened.

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 single-parameter tool with no output schema, the description covers the auth flow, config vs session approaches, and the no-args invocation. It is complete enough for an agent to invoke correctly, though it doesn't describe return values (which is acceptable without an output schema).

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 fully compensates. It explicitly documents the token parameter as a JWT to paste, and explains the no-argument case for retrieving the link. This gives complete semantic understanding of the only 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: authenticating with a JWT token or obtaining a login link. It specifies the resource (the MCP server) and the action (authenticate), and distinguishes from sibling tools by describing the specific auth flow for IDE agents.

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: permanent connection via config header vs session-only via token argument. It also explains when to call with no arguments to get a link. However, it does not explicitly mention alternatives or when not to use this tool.

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. The description adds detail on return behavior (authenticated:true, empty pending[], connect_url), which enriches the safety profile without contradiction.

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 sentences, front-loaded with the key purpose, and every word earns its place. No 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 zero-parameter read-only tool with rich annotations, the description fully covers the behavior, including edge cases (all providers connected vs missing credentials), and no output schema is needed.

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 parameters, the description has no parameter semantics to add. The baseline is 4 for 0-param tools, and the description effectively explains the tool's behavior, making it complete.

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 behavior around provider connections, which differentiates it from siblings like authenticate 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 gives context on when this is useful (checking connection status) but does not explicitly mention alternatives or when not to use it. It implies usage for connection verification but lacks 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?

The description discloses critical behaviors beyond annotations: invoke works without installing the MCP, connect/checkout retry flows, one-off vs permanent installation, and permission requirements for writes. This complements the annotations (readOnlyHint false) without contradiction and adds actionable context for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but each sentence earns its place, covering a complex multi-action tool and its numerous workflows. It is front-loaded with the core purpose and flows logically from MCP discovery to invocation to billing and the prompt library. Could benefit from bullet points, but it is not padded.

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 optional parameters and no output schema, the description covers all major workflows: search, describe, invoke, install, permissions, billing, and the prompt library. It omits some niche actions (e.g., 'resume') and parameter details, but the essential operational context is present and coherent.

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 compensates significantly by explaining the action enum values ('search', 'describe', 'invoke', 'install', 'list_tools', 'search_prompts', etc.) and how tool_id, mcp_id, and prompt_* parameters are used. However, not all 23 parameters are explicitly covered (e.g., immediate, tier_slug, prompt_targets), so it is not perfect.

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 the official mcp.ai marketplace/catalog and explains its dual role: discovering and running MCPs. It distinguishes itself from sibling tools by detailing the core flow (search → describe → invoke) and the prompt library, leaving no ambiguity about its purpose.

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 when-to-use guidance: 'Use install only to make an MCP PERMANENT in the active toolkit; prefer invoke for a single/occasional use.' It also contrasts the prompt library with MCP discovery, and lists the appropriate action for each scenario (list_tools, subscribe/cancel, report_bug, request_mcp).

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=false, destructiveHint=false, and idempotentHint=true, so the safety profile is clear. The description adds a small behavioral expectation by asking for the conversation array 'for reproduction,' which hints that the report is used for debugging. However, it does not disclose what happens after submission (e.g., ticket creation, data transmission to developers), so credit is limited.

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 sentences total, both information-dense. The first sentence states the purpose clearly, the second gives a key usage tip. No filler or repetition of schema details. Excellent economy of 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?

This is a simple feedback-reporting tool with no output schema and only three parameters. The description covers the core action and the most important usage tip (including conversation for reproduction). It does not explain return values or post-submission behavior, but for a tool of this complexity with solid annotations, the description is mostly complete. A small gap is the under-explained 'context' parameter and the string-array mismatch.

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 does clarify that 'message' is the content of the bug/feature/feedback and that 'conversation' is for reproduction, but it does not explain the 'context' parameter at all. Additionally, it calls 'conversation' an 'array' while the schema defines it as a string (likely a JSON-encoded array), which creates minor ambiguity. Partial compensation, not full.

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 clearly enumerates the resources ('a bug, missing feature, or feedback'). It distinguishes itself from sibling tools like authenticate and show_version, which serve completely different purposes, so no ambiguity about what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The only usage hint is 'Include the conversation array with recent messages for reproduction,' which addresses how to invoke the tool rather than when to choose it. No sibling tool is comparable, so differentiation is not required, but the absence of any contextual guidance results in a low score.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context by specifying the exact data returned ('platform and adapter versions'), going beyond the high-level safety hints. This helps the agent anticipate the response without knowing the 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, front-loaded sentence that immediately communicates the tool's function. Every word earns its place, with no redundancy or fluff. Perfectly sized for a tool of this simplicity.

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 version tool, the description is fully complete. It states what information will be returned (platform and adapter versions). No output schema exists, but the description sufficiently sets expectations. Nothing important is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4 per the rubric. Schema coverage is 100% (vacuously), and there is no parameter ambiguity. No additional description is required in this dimension.

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 identifies the exact resource ('the current MCP platform and adapter versions'). It clearly distinguishes this tool from siblings like 'authenticate' or 'connect' by focusing solely on version information. No ambiguity.

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 clearly implies when to use this tool: when version information is needed for the MCP platform or adapters. It doesn't state explicit alternatives or exclusions, but the purpose is so specific that usage context is evident. Slightly more explicit guidance (e.g., 'use in diagnostics') would earn 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing a safe, side-effect-free operation. The description adds value by detailing exactly what state is returned (installed MCPs, connection status, accounts, catalog tool counts), which supplements the annotations without contradicting them.

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, well-structured sentence that front-loads the core purpose and then lists the specific information returned. Every word 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?

For a zero-parameter, no-output-schema tool, the description provides sufficient detail about what the tool returns, covering the main aspects an agent would need to know. There is no missing information that would affect tool selection or invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description appropriately does not need to explain parameter meanings, as the schema is already complete with an empty property set.

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 and enumerates the specific contents (installed MCPs, connection status, accounts, catalog tool counts). The verb "Returns" plus the resource "toolkit state" is specific and distinguishes this from sibling tools like authenticate or connect, 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?

While there is no explicit "use this when" statement, the context is clear: an agent would call this tool whenever it needs an overview of the toolkit's configuration and connection status. The sibling tools are sufficiently different in function that confusion is unlikely, and no exclusions or alternatives are needed.

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 and idempotentHint, so description correctly matches. Adds cost, no-credentials, and LGPD context, which aids understanding. Doesn't mention return format but that's not required.

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?

Concise, purpose first, then context. Slightly verbose with legal disclaimers but acceptable.

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?

Many parameters, no output schema, and the description gives no guidance on how to use the parameters or what to expect in return. Incomplete for a complex 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?

Description does not explain any of the 8 parameters. Schema coverage is 0%, and the description must compensate but does not.

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?

Clearly states the tool queries official Brazilian court sources for Colégio Recursal, with a specific verb (consultar) and resource. Distinguishes from siblings which are generic platform 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?

Provides context (official source, paid per query) but no explicit when/when-not vs alternatives. Since siblings are unrelated, no exclusions needed, but lacks clear guidance on usage scenarios.

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