Prefeitura SP São Paulo: 2ª Via da Taxa de Elevadores

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

Annotations indicate readOnlyHint=false and destructiveHint=false, while idempotentHint=true. The description adds value by explaining the token's life span (permanent vs session-only), the two usage modes, and that calling with no args returns a link. It does not contradict annotations and provides behavioral context beyond what annotations already convey.

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 relatively compact for the complexity it covers, being front-loaded with the tool's purpose and the recommended permanent setup. It uses a compact structure with actionable steps, though it packs multiple clauses into a long first sentence, slightly hurting readability.

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 annotation set (idempotent, non-destructive) and the single optional parameter, the description covers the essential context: login flow, token usage, and the two modes. It even mentions an alternative setup (config header) and explains the session-only vs permanent distinction. However, it doesn't describe the returned link's format or failure scenarios, so a small gap remains.

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

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

The schema has only one optional string parameter 'token' with 0% description coverage, so the description must compensate. It explains that 'token' should contain the JWT pasted by the user for session-only login, which adds meaning beyond the schema. However, it doesn't detail token format requirements or what happens if an invalid token is provided, so rich semantics are partially covered.

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: to authenticate an IDE agent (like Cursor) with the MCP.AI server by logging in via browser and obtaining an access token. It distinguishes itself from siblings by providing a specific authentication flow with setup options, though it does not explicitly contrast with sibling tools like 'connect'.

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 both permanent setup (adding a header to the server config) and session-only login (pasting the token). It also gives clear usage context—when to call with a token versus without args—and even clarifies when to use this tool versus alternatives (e.g., adding to config for permanent connection).

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, read-only operation. The description adds valuable context beyond annotations by explaining the exact return behavior under two different conditions (all providers connected vs. missing credentials), including the presence of 'pending[]' and 'connect_url'. This enriches the agent's understanding without contradicting any annotation.

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

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

The description is two sentences, front-loaded with the core purpose ('Returns connection status and URLs'), and provides additional details in a compact, efficient manner. Every phrase earns its place with no redundant or filler content.

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, and strong annotations covering safety), the description adequately covers the return values and their conditional behavior. It explains 'authenticated:true', 'pending[]', 'connect_url', and per-install URLs. While it could elaborate further on the exact structure of 'pending[]', the brevity is acceptable for the tool's low complexity.

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, and schema coverage is 100%. Per the rubric, the baseline for zero parameters is 4. The description adds no parameter semantics because there are none to describe, but the baseline applies.

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 distinguishes itself from sibling 'authenticate' by specifying it's a status check rather than an action. The description also clarifies the output under different conditions, making 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?

The description implies when to use it: to check connection status and retrieve URLs when credentials are missing. It does not explicitly mention alternatives or state 'use this when...', but the context is clear enough for an agent to infer appropriate usage, especially given the sibling tool 'authenticate' exists for actual authentication.

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?

Discloses key behavioral traits beyond annotations: one-off invoke avoids installing, writes require workspace owner/admin, auth and payment failures surface as connect/checkout links, and search/describe flag installed_in_toolkit vs installed_in_workspace. 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?

Dense and front-loaded with the main purpose and core flow; every sentence adds substance. However, it is one long paragraph that could benefit from separating MCP flow, permissions, and prompt-library concerns, and 'pontualmente' is an unnecessary non-English insertion.

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 complex 14-action dispatcher with no output schema, the description covers the main flows, permissions, auth/payment behavior, and prompt library well. It omits explicit detail on the 'resume' action and exact return shapes, but overall it is a strong contextual guide.

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 enum and the mcp_id/tool_id/arguments-related flow, and gives high-level meaning to prompt-library operations. However, with 23 params and 0% schema description coverage, many optional parameters such as limit, immediate, tier_slug, cancel_reason, report_context, request_details, and several prompt_* fields are left 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?

Description clearly identifies the marketplace as the in-platform catalog of MCPs/tools and the way to run them, with an explicit search → describe → invoke flow. It also distinguishes its action families from sibling tools like report_bug and authenticate.

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 concrete when-to-use guidance: prefer invoke for one-off use, use install only for permanent toolkit membership, use list_tools for currently callable tools, and use request_mcp when nothing fits. It explicitly contrasts invoke with install and explains the credential/checkout link retry flow.

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 does not disclose any behavioral aspects such as return format, error handling, or side effects. It only mentions billing and LGPD compliance, which are not relevant to the tool's operational 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 run-on sentence overloaded with legal and billing text. It is not concise or well-structured, making it difficult to extract the essential 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?

There is no explanation of expected outputs, parameter meaning, or any operational context. The tool is effectively underdocumented, providing no actionable information beyond a generic legal disclaimer.

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 parameters 'guia', 'chapa', and 'data_vencimento' are completely unexplained. The description does not indicate what these values represent or how they should be formatted, leaving the agent unable to construct a valid request.

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 vaguely mentions '2ª Via da Taxa de Elevadores' (second copy of elevator tax) but is buried in legal disclaimers. It does not clearly state the tool's function or distinguish it from sibling tools 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?

No guidance is provided on when to use this tool versus alternatives. The description lacks any context about scenarios, prerequisites, or when it should be invoked.

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 does not disclose any behavioral consequences beyond the basic action. Annotations indicate idempotent and non-destructive, but the description adds no insight into side effects or expected outcomes of reporting.

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 brief and to the point, with no redundant wording. Two sentences cover the core purpose and a key usage detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, and the description adequately conveys its purpose and a critical usage aspect. It does not need to explain return values or complex side effects, so the coverage is sufficient.

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 'conversation' parameter (needed for reproduction) but leaves 'context' and 'message' unexplained. Since the schema has no descriptions, this partial coverage adds moderate value.

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 function: reporting bugs, missing features, or sending feedback. It also differentiates from sibling tools, none of which serve this 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?

The description implicitly defines when to use the tool (when reporting bugs/feedback) and provides a specific usage instruction about including the conversation array for reproduction. It does not explicitly contrast with alternatives, but no alternative exists among siblings.

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 supply readOnly, idempotent, and non-destructive flags. The description adds no behavioral context beyond the simple 'show' action, which is consistent but not extra informative. Given annotations cover safety, a neutral score is appropriate.

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, clear sentence with no redundant words. It is perfectly 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?

With no parameters and no output schema specified, the description fully explains the tool's function. It doesn't need to elaborate on return values or side effects; the purpose is explicit and 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?

There are no parameters, so the schema coverage is effectively 100%. According to the rubric, the baseline is 3 even without parameter descriptions. The tool requires no input, so this is adequate.

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 function with a specific verb ('Show') and resource ('current MCP platform and adapter versions'). It is unambiguous and distinguishes from 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 guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context. The description lacks any 'when to use' information.

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 safety is covered. The description adds value by detailing the contents of the returned state (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond structured fields and aids the agent's expectation.

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 action and then lists the concrete components of the return value. Every word contributes information, with no redundancy or padding.

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 no output schema, the description provides a thorough breakdown of what the tool returns. It fully describes the toolkit state composition and is sufficient for an agent to use the tool effectively.

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 takes zero parameters, so the baseline of 4 applies. The description correctly focuses on the return value rather than parameter details, and there are no parameters that need semantic explanation.

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 the specific verb 'Returns' and clearly identifies the resource as 'current toolkit state'. It enumerates exactly what is included (installed MCPs, connection status, accounts, catalog tool counts), which differentiates it from sibling tools like show_version or connect.

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 it—whenever you need an overview of the toolkit state—without explicitly naming alternatives or exclusions. The context is unambiguous and does not conflict with sibling tools, but it lacks explicit 'use this instead of...' guidance.

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