Prefeitura RJ Rio de Janeiro: Certidão de Elementos Cadastrais - IPTU

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

Annotations already indicate idempotent and non-destructive. The description adds context about session versus permanent login, token handling, and that no args returns a link. No contradiction with annotations, and it provides meaningful behavioral detail beyond the minimal annotation info.

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?

Extremely concise: every sentence adds value. It covers purpose, permanent method, session method, and no-args behavior in just two sentences, well front-loaded with the main context.

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?

No output schema, but the description covers both usage modes and return behavior for no args. It doesn't mention error handling or prerequisites, but for a simple authentication tool the description is sufficient for an agent to invoke it 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 provides only the token property with no description (0% coverage). The description fully explains the token as a JWT and how to use it, and clarifies it is optional via the no-args case, adding essential meaning beyond the raw 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 the tool authenticates to MCP.AI for IDE agents, with a specific verb 'log in' and resource. It distinguishes from siblings like connect and marketplace by specifying its intended use 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?

The description gives explicit usage instructions for both permanent (config header) and session-only (token) authentication, plus the no-args case. It doesn't explicitly mention alternatives, but the 'Best' recommendation provides clear preference within the tool's own methods.

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 clear. The description adds context about the two states (authenticated:true vs pending[] with connect_url) and what the response contains, which is useful. However, it doesn't disclose any potential side effects or edge cases beyond that. Since annotations cover the main behavioral traits, the description adds some value but not extensive. Score 3 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 two sentences long, front-loaded with the purpose, and provides the key conditional behavior without any fluff. Every sentence adds value: the first states the primary function, the second explains the two states. Perfectly concise.

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 that the tool has no parameters, no output schema, and annotations cover the safety profile, the description is quite complete. It explains the return values (authenticated, pending, connect_url) and the conditions for each. A minor gap is that it doesn't mention if there are any other fields like per-install URLs format, but it explicitly says 'per-install URLs'. Overall, it's complete for a simple status-check 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?

The tool has zero parameters, so the schema covers 100% by default. The description explains what the response contains (connection status, URLs, pending array), which helps the agent understand the output. Since there are no parameters, the description doesn't need to explain parameter semantics; the high schema coverage and zero params mean the baseline is high. The description adds value by explaining the output, so a 4 is warranted.

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, which is a specific resource with a clear state-dependent — the tool provides purpose of the verb’s value that is unclear. The purpose is clear and well-defined: it reports connection status. It is likely to a clear definition’s not only to the primary purpose that the criteria for a particular outcome.

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 if all providers are connected (when authenticated:true and empty pending[]) or to get URLs when credentials are missing. However, it does not explicitly state when NOT to use it or name alternative tools. Given the sibling tools, it could mention that authenticate is for establishing connections, but it doesn't. Still, the description provides clear context about the scenarios (all connected vs missing credentials), so a 4 is warranted.

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 goes well beyond the annotations, disclosing that invoke works even when the MCP is not installed, may return connect or checkout links, and that writes require workspace owner/admin. It also explains the prompt library is separate. No contradictions with annotations (readOnlyHint: false aligns with write operations).

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 appropriately sized for the tool's complexity (23 params, many actions). It is front-loaded with a clear definition and flows logically from the core marketplace concept to the action distinctions, then to the prompt library. Every sentence contributes without 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?

Despite no output schema, the description explains expected outcomes for key actions (e.g., invoke returns connect/checkout links, describe returns full profile). It covers permissions, distinguish between install/invoke, and describes the prompt library. This is comprehensive for the tool's complexity and the minimal annotations.

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 by explaining key parameters like action, mcp_id, tool_id, and arguments in context. It also touches on prompt-related params (prompt_slug, prompt_body, prompt_vars). However, it does not explain minor parameters like limit, query, message, immediate, tier_slug, cancel_reason, etc., leaving some ambiguity for those without default expectations. Still, the description adds substantial meaning for a complex 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 clearly identifies this as the official mcp.ai marketplace, with a specific purpose of cataloging and running MCPs/tools. It explicitly outlines the core flow (search → describe → invoke) and distinguishes itself from sibling tools by covering a broad set of marketplace actions, including the prompt library.

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 guidance on when to use invoke vs install (prefer invoke for one-off use, install for permanence) and explains the search-describe-invoke flow. It also clarifies that list_tools shows what's callable now, and mentions permission requirements for writes. While report_bug appears as both a sibling and a sub-action, the description still clarifies its role within 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 provide readOnlyHint, idempotentHint, etc. The description adds value by noting payment via prepaid credits, no platform credentials, and LGPD compliance/client responsibility. It also clarifies data is not confidential. This goes beyond annotations and enriches behavioral 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?

The description is a single paragraph of about 40 words, front-loaded with the purpose. Additional sentences on payment and LGPD are relevant. It's concise without fluff, though it could be tightened slightly.

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 read-only tool, the description covers the source, payment, and legal aspects. However, missing parameter semantics and no mention of output or error behavior leave it incomplete. It's adequate but has clear gaps.

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 only parameter 'inscricao' is a string, but the description gives no explanation of what it means (likely IPTU registration). Schema coverage is 0%, so the description must compensate, but it doesn't. This is a significant gap for proper usage.

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 it's a consultation of official certification of cadastral elements for IPTU in Rio de Janeiro. It uses a specific verb 'consulta' and distinguishes it from sibling tools like auth, marketplace, etc. The core purpose is 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 usage for querying official Brazilian sources, even mentioning it's the same info available to citizens. It doesn't explicitly say 'use when...' but the context is clear. No exclusions needed since no sibling tool overlaps. Slightly indirect but acceptable.

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 the safety profile (idempotentHint true, destructiveHint false, readOnlyHint false), so the bar is lower. The description adds the useful context that the conversation array aids reproduction, but it doesn't disclose what happens after reporting (e.g., ticket creation, response, or side effects). This is a modest addition 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 sentences with no wasted words. The purpose is front-loaded, followed by a single actionable instruction. 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, the description covers purpose and a key usage detail. It doesn't mention output/confirmation or the optional context parameter, but the schema covers requiredness and defaults. Overall adequate, though it could briefly note what the user should expect after submitting.

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 explicitly explains the conversation parameter's purpose ('recent messages for reproduction'), but message and context are left implicit. Message's role is inferable from the tool's purpose, but context remains unexplained, leaving a partial gap.

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' with clear targets ('bug, missing feature, or send feedback'), making the tool's function immediately obvious. It also distinguishes itself from unrelated sibling tools (authenticate, connect, marketplace, etc.) by its explicit 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 implies when to use the tool (when reporting bugs or providing feedback) and gives a concrete guideline: include the conversation array for reproduction. It doesn't mention exclusions or alternatives, but the sibling tools are unrelated, so no differentiation is 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=true, idempotentHint=true, and destructiveHint=false, covering safety traits. The description adds specific context about what exactly is returned (platform and adapter versions), which is useful beyond the annotations. No contradictions or missing essential behavioral 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, front-loaded sentence that conveys the entire purpose without wasted words. It is highly efficient and earns every character.

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, no complexity) and the annotations that already establish safety, the description fully covers what the tool does. There is no missing information that would leave an agent uncertain about invocation or expected outcome.

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 correctly omits parameter details. Per the rubric, a baseline of 4 is warranted for no parameters, and the description does not need to compensate for any schema gaps since there are none.

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 resource ('current MCP platform and adapter versions'), making its purpose immediately clear. It distinguishes itself from sibling tools like 'toolkit_info' by focusing on version display rather than general toolkit information.

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 the tool—whenever version information is needed—without ambiguity. It does not explicitly mention exclusions or alternatives, but given the simplicity and standalone nature of the tool, clear context is sufficient; no conflicting guidance exists.

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, so the safety profile is well-covered. The description adds valuable context by enumerating exactly what the state contains (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotation's generic 'read-only' signal. It does not mention rate limits or data freshness, but for a state-query tool this is sufficient.

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 core action ('Returns the current toolkit state') and then uses a colon to introduce a concise, enumerative list of the state's components. Every word earns its place, and it is easily scannable.

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 parameterless, read-only query tool with no output schema, the description fully covers what an agent needs to know: the tool's inputs (none) and the nature of its output (state details). It is complete and leaves no critical gaps in understanding.

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 baseline is 4. The description effectively explains what the response contains, which is the most relevant semantic information for an agent. There are no parameters to document, and the description makes it clear the tool takes no input.

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 'Returns' and a precise resource 'current toolkit state', followed by detailed contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This distinguishes it from sibling tools like 'show_version' (version info) and 'connect' (establish connection), 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?

The description provides clear context: use this tool to obtain toolkit state, which implicitly differentiates it from siblings like 'authenticate' or 'marketplace'. However, it lacks explicit 'when to use' vs 'when not to use' language or named alternatives. The context is clear enough for an agent to know when to invoke it, but it doesn't explicitly state exclusions.

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