Tribunal TSE: Título Eleitoral

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

Annotations indicate idempotent, non-destructive. Description adds behavioral context: browser login required, token can be stored permanently via config or session-only, and that calling with no args returns a link. 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 slightly verbose but well-structured, front-loaded with purpose and actionable steps. Each sentence adds value, though it could be tightened slightly without losing clarity.

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 optional parameter tool with no output schema, the description covers all use cases: session vs permanent, how to initiate, and integration context. No gaps for an agent to invoke correctly.

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 has only 'token' with no description, but the description explains its usage precisely: 'call with { token: "<jwt>" } after user pastes, or with no args to get link'. Fully compensates for schema coverage of 0%.

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 this tool authenticates the user, with explicit steps for browser login and token handling. It distinguishes from siblings (connect, marketplace, etc.) by focusing solely on 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?

Provides explicit instructions: call with no args to get link, call with token for session login, or add config header for permanent connection. Clearly explains when to use each method and the context (IDE agents).

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 strong behavioral hints: readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false. The description adds contextual behavior like what the return values mean (pending[] array, connect_url) and the conditional nature based on connection state. It doesn't contradict annotations. With annotations covering the safety profile, a 3 is appropriate as the description adds useful state-dependent 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 two sentences, both informative with no fluff. It front-loads the primary purpose and then details conditional behavior. Every clause earns its place. Excellent conciseness.

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 has no parameters, no output schema, but strong annotations, the description is quite complete. It explains the key states (authenticated:true and empty pending[] vs. missing credentials returning URLs). It could potentially mention what pending[] contains or more details about the URLs, but for a simple status tool, this is adequate.

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 does not need to explain parameter semantics. According to the rubric, 0 params = baseline 4. The description correctly focuses on return states rather than 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's purpose: 'Returns connection status and URLs.' It uses a specific verb ('returns') and resource ('connection status and URLs'). While it doesn't explicitly differentiate from siblings, the context of sibling tools like 'authenticate' and 'toolkit_info' implies this is a status check tool, but the description could have been more explicit about its role vs. those.

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: 'When all providers are connected...' and 'When credentials are missing...'. It explains the return values in different states, giving the agent guidance on expected outcomes. It doesn't explicitly mention alternatives, but given the sibling tools, the usage scenarios are well-defined.

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 say readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds crucial behavioral context: invoke runs one-off without installing or bloating the toolkit, install makes permanent, auth failures produce connect links, unpaid tools produce checkout links, and writes like install/uninstall/subscribe/cancel require workspace owner/admin. This goes well beyond the annotations and outlines real-world side effects and prerequisites.

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 information-dense; every sentence contributes to explaining a different action or behavior (flow, install vs invoke, auth, billing, prompt library). The core flow is front-loaded and uses arrows for clarity, though it is a single continuous paragraph that could benefit from bullet points or section breaks to aid scanning.

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, 14 enum actions, no output schema, and minimal annotations, the description is remarkably complete: it covers auth requirements, paid vs free behavior, permanent vs one-off installation, installed flags, prompt sharing, and when to use request_mcp. The main gaps are lack of per-action parameter mappings and any description of success return payloads, but the operational context needed to invoke correctly is largely present.

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% across 23 parameters, so the description must compensate. It explains the 'action' enum in depth and clarifies core parameters like tool_id ('pick the right tool_id → invoke RUNS that tool') and prompt-related fields. However, many parameters such as limit, query, arguments, immediate, tier_slug, cancel_reason, report_context, and prompt_targets are not explicitly tied to their actions, leaving the agent to rely on names alone.

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 immediately defines the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them', giving a clear, specific mission. It further enumerates the core actions (search, describe, invoke, install, list_tools, etc.) and even hints at scope boundaries (prompt library vs MCP catalog), making it easy to distinguish 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 gives explicit when-to-use guidance: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use' and 'request_mcp asks us to build a NEW MCP when nothing fits'. It also explains the core flow and how invoke differs from install, plus when credential or payment links appear, which directs the agent's decision-making beyond just what the tool does.

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 indicate readOnlyHint: false, destructiveHint: false, and idempotentHint: true. The description does not conflict with these, but it adds little beyond what annotations imply. It mentions requiring the conversation array for reproduction, which is a mild behavioral detail, but does not address output, side effects (e.g., creates a ticket), or idempotency concerns. Given the annotations already cover read/write status, the description provides only marginal additional 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?

Two sentences, zero fluff. The first sentence states purpose; the second gives a concrete usage hint. 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 reporting tool, the description is adequate but not rich. It explains the purpose and hints at the need for conversation messages, but given annotations (idempotent, non-destructive) and no output schema, it could still benefit from mentioning what happens after reporting (e.g., confirmation) or any prerequisites. It's a minimum viable description.

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 parameter descriptions), but the description adds meaning to the 'conversation' parameter by stating to include it for reproduction. However, it calls it a 'conversation array' while the schema declares it as a string, which is a mismatch that could confuse the agent. The 'context' parameter is left unexplained. The description compensates partially but is incomplete.

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: 'Report a bug, missing feature, or send feedback.' This is a specific verb-resource combination and distinct from siblings like authenticate, connect, or marketplace, which are all unrelated to reporting issues.

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 it ('Report a bug, missing feature, or send feedback') and gives a concrete usage instruction: 'Include the conversation array with recent messages for reproduction.' It doesn't explicitly exclude any situations, but the context is clear enough for an agent to know when to invoke it.

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 non-destructive behavior, so the description only needs to add context. It adds that the tool reads current platform and adapter versions, which is useful for an agent predicting output. 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?

Single sentence, directly front-loaded, and contains no filler. Every word contributes to defining the tool's purpose.

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 utility with strong annotation coverage, the description is sufficient. It could mention return format, but the low complexity means the current detail is adequate for selection and 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 parameter semantics are trivially clear and the baseline of 4 applies. There is nothing for the description to add beyond confirming no inputs are required.

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 uses specific verb 'show' and clearly identifies the resource as current MCP platform and adapter versions. It distinguishes this utility from other sibling tools like authenticate or 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?

No explicit guidance on when to use this tool versus alternatives, though siblings are functionally distinct. Usage context is only implied: call when needing version information. It does not state exclusions or prerequisites.

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 well covered. The description adds value by specifying exactly what information is returned (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotations. No 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?

The description is a single, well-structured sentence that front-loads the main purpose ('Returns the current toolkit state') and then lists the specific components. 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?

Given the tool has no parameters, no output schema, and simple annotations, the description is complete enough. It clearly enumerates what the return value contains, which is the main thing an agent needs to know. It could mention that it's a snapshot/read-only operation, but the annotations already cover that.

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 doesn't need to explain parameter semantics. The baseline for 0 params is 4, and the description appropriately focuses on the output content rather than parameters.

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 returns the current toolkit state, listing installed MCPs, connection status, connected accounts, and catalog tool counts. This is specific and distinguishes it from sibling tools like authenticate or connect, which are action-oriented.

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 a read-only informational tool to be used when checking the toolkit's state, but it does not explicitly state when to use it versus alternatives. However, given the sibling tools are all action-oriented (authenticate, connect, etc.), the usage context is clear enough.

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 destructiveHint=false; the description does not contradict these and adds substantial context: the source is official and public (same as available to citizens), the data is not confidential, no platform credentials are needed, there's a pay-per-query pricing model, and the client bears LGPD controller duties. This meaningfully enriches the safety and cost profile.

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?

Three dense sentences, each earning its place: purpose/source, platform/cost model, and legal/compliance framing. The text is front-loaded with the tool's function and contains no filler. It loses a point for being slightly dense in the final sentence, but remains appropriately sized for the information it conveys.

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?

With no output schema to clarify return values and no param descriptions in the schema, the description needed to explain what data is returned and how inputs map to a lookup; it does neither. It covers legal and pricing aspects well but omits functional details like response content and which optional-field combinations constitute a valid query, making it incomplete for a 6-parameter, paid, query-style 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 had to compensate but provides zero parameter information. The parameter names (cpf, name, father, mother, birthdate, titulo_eleitoral) are self-explanatory Portuguese terms, which saves it from a 1, but no formats (e.g., date format, CPF masking/validation) or guidance on valid combinations is given. The unusual fact that only 'birthdate' is required is unexplained.

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 specific verb+resource: 'consulta' of 'Título Eleitoral' via 'Tribunal TSE' with an official official source. It's clear this is a read/query operation on voter registration data. Loses a point because it doesn't add granularity on the exact distinction from any sibling (though siblings like 'authenticate' are dissimilar) or clarify exactly what data is returned.

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?

No explicit when/when-not guidance or alternatives are mentioned. It gives operational context (no credentials needed, pay-per-query, prepaid credit) and a legal caveat (client is data controller under LGPD), but these are conditions of use rather than guidance on when to select this tool over others. The LGPD note implies a legitimate-purpose boundary, but this is not developed.

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