Correios: Completa CEP (CEP + Área territorial brasileira)

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

The description discloses the session behavior ('session-only login') and the permanent config option, adding context beyond the idempotentHint annotation. However, it doesn't explain what happens if an invalid token is provided or whether the operation invalidates existing sessions. It doesn't contradict the annotations—idempotentHint:true is consistent with a fire-and-forget authentication setup—but the explanatory burden is only partially met. The description provides some insight into side effects, but not exhaustively.

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 that crams multiple instructions and alternatives, making it harder to parse. It front-loads the purpose but then meanders through configuration options, sentences like 'MCP.AI solo for IDE agents (Cursor, etc.):' are awkwardly placed. It's compact but not well-structured, and the flow could be improved with bullets or more deliberate punctuation.

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 one optional parameter and no output schema, the description covers the main scenarios: permanent config via header, session-based token, and no-arg link retrieval. It doesn't explain error cases or what happens after authentication, but given the simplicity of the tool, this is largely sufficient. The integration with server config is a good contextual detail that aids the agent.

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 a schema that only defines 'token' as an optional string and 0% schema description coverage, the description carries full responsibility for explaining the parameter. It explains that 'token' expects a JWT and that omitting it returns a link. This meaningfully adds to the minimal schema, though it could be more explicit about the exact format or give an example. Still, it compensates well for the lack of schema hints.

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 handles authentication, with a specific verb ('authenticate') and resource (the MCP server's connection to the IDE agent). It explicitly describes the login flow and token usage, distinguishing it from sibling tools like 'connect' or 'marketplace' which serve different purposes. The focus on browser login and token handling leaves no ambiguity about its role.

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 concrete usage guidance: the recommended approach (configure via header), the alternative (pass token in the call), and the no-arg option to retrieve a link. It implicitly tells when to use each variant, though it doesn't explicitly say when not to use the tool or contrast with alternatives like 'connect' beyond the content. This is clear operational 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds behavioral details about the response in two scenarios (all providers connected vs. missing credentials), including that it returns connect_url and per-install URLs. This is useful and does not contradict 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 two sentences, both front-loaded with the core function. No fluff, every word adds value. It efficiently covers the main output and special cases.

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 0-parameter, read-only status tool, this description is complete. It explains the response states (connected vs missing credentials) and the URLs returned. No output schema is provided, so the description suffices as the only behavioral documentation.

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 any. Baseline for no parameters is 4, and the description doesn't mention parameters because there are none. It focuses on the output, which is appropriate.

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: 'Returns connection status and URLs.' It goes beyond a generic purpose by detailing two specific response states (when all providers are connected vs. when credentials are missing), making the tool's scope immediately understandable. There's 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 explains what the tool returns under different conditions, which implicitly guides when to call it (to check connection status). It does not explicitly reference sibling tools like 'authenticate', but the mention of per-install URLs and toolkit URLs provides actionable context. Missing an explicit 'use this if you need X' might be a slight gap, but the purpose 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, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context: it discloses hosting ('Hospedado pela plataforma'), payment requirements ('pague por consulta com crédito pré-pago'), data source ('fontes e órgãos oficiais brasileiros'), and that data is not confidential ('não é dado sigiloso'). It also states the client's LGPD responsibility, which is beyond the annotations. 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 one long paragraph but is front-loaded with the core purpose in the first phrase. It includes multiple sentences about payment, data source, and LGPD, which are useful but could be tightened. It is not excessively long, yet not maximally concise; each sentence adds value, but the structure could be bullet-pointed for 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?

With a single parameter, no output schema, and decent annotations, the description covers key aspects: it states the return scope (CEP + territorial area), payment model, data source, and legal responsibilities. It does not describe the output format or error handling, but given the simplicity of the tool and the explicit mention of what is returned, it is reasonably complete for an agent to understand the context.

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 for the lone 'cep' parameter. However, the description does not explain the expected format (e.g., digits only, with/without hyphen), validation rules, or any constraints on the input. The only hint is the term 'CEP', which may be widely understood, but the description fails to provide actionable input guidelines, leaving the agent to guess the exact format.

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: 'Completa CEP (CEP + Área territorial brasileira), consulta em fonte oficial.' This explicitly names the resource (CEP) and the action (consulta/completion), and distinguishes it from the general sibling tools (authenticate, connect, etc.) by specifying the Brazilian postal code lookup and territorial area.

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 complete CEP data ('consulta em fonte oficial') and mentions payment per query, but it does not explicitly state when to use this tool versus alternatives, nor does it give exclusions or conditions. The context is implied rather than explicit, and no alternative tool is named.

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?

Despite annotations carrying readOnlyHint=false/destructiveHint=false, the description adds substantial behavioral context beyond them: writes require workspace owner/admin privileges, invoke performs a hidden one-off install that does NOT bloat the toolkit, auth-missing returns a connect link, empty-wallet paid tools return a checkout/top-up link requiring user action then retry. It also discloses that search/describe flag installed_in_toolkit vs installed_in_workspace. No contradiction with annotations. Rich safety and side-effect disclosure.

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?

Every sentence earns its place in terms of content density — there is genuine informational value throughout. However, it is one continuous wall-of-text paragraph with no structural breaks, bullets, or section delineation, which is poor for an aggregate tool managing 14 sub-actions and two feature domains (MCPs + prompt library). The information is complete but the formatting substantially harms scannability for an agent that must rapidly extract action-specific guidance.

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 this complex (14 actions, 23 params, no output schema), the description is remarkably complete: it covers the discovery workflow, the install-vs-invoke decision, auth and payment edge cases with retry semantics, permission/ownership requirements, the prompt library sub-domain, and secondary actions (list_tools, subscribe/cancel, report_bug, request_mcp). Gaps exist only on individual parameter returns and some output-shape details, which is understandable given no output schema exists.

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 across 23 parameters, the description bears the full explanatory burden. It does contextualize the most critical parameters well: the action enum (all 14 values explained), tool_id ('so you pick the right tool_id' from describe's profile), mcp_id, prompt_slug, and prompt_vars ({{variables}} filled). However, several parameters get zero coverage: immediate, tier_slug, conversation, arguments, limit, query, message, cancel_reason/comment, report_context, request_details. It compensates for the primary parameters but leaves many secondary ones 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 is exceptionally specific about what this aggregated hub tool does: it's the mcp.ai marketplace catalog AND the execution engine for MCPs, plus a prompt library. It enumerates all 14 sub-operations (search→describe→invoke core flow, install/uninstall, billing, prompt library) and clearly differentiates the marketplace's role from siblings like authenticate/connect (auth happens via returned connect links, not in this tool).

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?

Outstanding when-to-use guidance: explicitly directs 'prefer invoke for a single/occasional use' versus 'Use install only to make an MCP PERMANENT in the active toolkit', explains the retry-after-payment/connect-link flow, names list_tools for current callables, and states request_mcp for 'when nothing fits'. The search→describe→invoke core flow is spelled out as a decision sequence. This is the model of usage differentiation.

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 annotations indicate idempotentHint=true and readOnlyHint=false, but the description does not explain the side effects (e.g., creating a ticket, sending a message). It doesn't state what happens after reporting or if any permissions are needed.

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 short sentences convey the essential information without fluff. It is front-loaded with the primary action and clearly states what to include.

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, it explains the main param (conversation) and purpose. However, it doesn't mention what happens after reporting, nor does it clarify the 'context' parameter, leaving some 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 description mentions 'conversation array' explicitly, giving context for that parameter that the schema lacks. However, 'context' is not explained, and 'message' is only implied. With 0% schema description coverage, more detail would be helpful.

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 purpose: 'Report a bug, missing feature, or send feedback.' This is unambiguous and directly tells the user what the tool does. The title 'Report Bug' reinforces this.

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 says to include the conversation array for reproduction, but does not specify when to use this tool versus other siblings like 'marketplace' or 'show_version'. Also lacks prerequisites or conditions for use.

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 no extra behavioral context beyond the resource and action, such as return format or side effects. It is consistent with annotations but contributes little beyond 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, direct sentence with no filler. It front-loads the action and resource, earning its place entirely.

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 with no output schema, the description is sufficient. It tells the agent exactly what the tool does and what resource it accesses, leaving no ambiguity.

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 description coverage is 100% (empty schema). The description doesn't need to explain parameters, so the baseline of 4 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 states 'Show the current MCP platform and adapter versions,' using a specific verb ('Show') and resource ('MCP platform and adapter versions'). This clearly distinguishes it from siblings like authenticate or report_bug, which serve 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?

Usage is implied by the description: use this when you need version information. However, there is no explicit mention of when to use it over the sibling toolkit_info or any exclusions/alternatives, so it only meets the 'implied usage' level.

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 beyond the readOnlyHint annotation by specifying exactly what state is returned (installed MCPs, connection status, accounts, counts). It adds meaningful context without overpromising, though it does not address potential latency or failure modes.

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 maximizes information density. Every clause adds value, and there is zero 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?

For a parameterless read-only tool with annotations and no output schema, the description fully covers what the tool returns and when it is relevant. No gaps in context are evident.

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 per the rubric, the baseline score is 4. The description adds no parameter details, but none are 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 clearly states the tool 'returns the current toolkit state' and enumerates specific data points (installed MCPs, connection status, accounts, catalog tool counts), distinguishing it from siblings like show_version or marketplace. The verb+resource structure is explicit and 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 context for using this tool is obvious—retrieve toolkit state—but it does not explicitly mention when not to use it or alternatives. Since siblings like connect and authenticate serve different purposes, the implied usage is clear, yet it stops short of explicit guidance.

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