ECAC: Caixa Postal

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

Annotations already declare idempotent and non-destructive. The description adds valuable context about the behavior: two authentication modes with different persistence (permanent vs. session-only), and that calling with no args returns a link. This goes beyond the annotations by clarifying the side effects and interaction pattern.

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 lengthy but well-structured, with clear separation between the permanent and session-only methods. Every sentence adds information, and the key points are front-loaded with the purpose stated first.

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 and a single optional parameter, the description covers the essential behavior, including both invocation modes and the result (link vs. session). It is complete enough for an agent to understand what to do, though it could mention the return value in more detail.

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 by explaining the optional 'token' parameter and the no-argument behavior. It explicitly spells out the invocation format and the meaning of the JWT token.

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 MCP.AI with IDE agents via browser login and token exchange. It specifies the resource (MCP.AI for IDE agents) and the action (log in, copy token), distinguishing it from sibling tools like 'connect' which likely serve a different function.

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 usage scenarios: permanent connection via config header vs. session-only login by passing token or no args. It does not explicitly mention alternatives among sibling tools, but it gives clear contextual instructions for when to use each mode.

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?

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses state-dependent behavior: when all providers are connected it returns authenticated:true and empty pending[], and when credentials are missing it returns connect_url for the toolkit and per-install URLs. This adds valuable detail about return values and edge cases that annotations do not cover.

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 main purpose, and every word is necessary. It efficiently conveys both the general behavior and the conditional output details 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?

This is a simple status-check tool with no parameters and no output schema. The description adequately explains the return values in both scenarios (connected vs missing credentials), which is the main contextual information an agent needs. It is complete for the tool's 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 zero parameters, and the input schema is an empty object with 100% coverage. Per guidelines, a baseline of 4 is appropriate for no parameters. The description does not need to add parameter info, and there is nothing to compensate for.

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.' This specifies the verb and resource, and distinguishes it from siblings like 'authenticate' (which presumably initiates connections) and 'show_version' (which returns version info). The conditional detail about authenticated:true vs connect_url further clarifies the 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 for when to use this tool: to check connection status and obtain URLs. It implies this is the read-only status-check counterpart to 'authenticate', though it does not explicitly say 'use this instead of authenticate' or 'when credentials are missing, use connect to get the connect_url.' The context is clear but exclusions are not stated.

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=true and destructiveHint=false, and the description adds valuable context: it's hosted by the platform, requires no platform credentials but uses prepaid credits, and deals with non-confidential official data. It also clarifies data privacy aspects (LGPD). This goes beyond the annotation hints, though it doesn't detail side effects or error behaviors.

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 concise (four short sentences in Portuguese) and front-loads the main purpose early. No wasted words, but it could be even more streamlined. It's well-structured and to the point.

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 lack of an output schema and zero parameter descriptions, the description should explain the tool's behavior more thoroughly. It fails to explain what the query returns, how the certificate parameters are used, or any prerequisites (e.g., having prepaid credits). The absence of such details makes it incomplete for an agent to use 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?

Schema coverage is 0% (no parameter descriptions). The description does not explain any of the six parameters (pkcs12_cert, pkcs12_pass, ignora_lidas, etc.). It adds no meaning to the parameters, leaving the agent with only names (some in Portuguese) and no hint of formatting or purpose. This is a major 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 states a specific verb ('consulta' - query) and resource ('Caixa Postal' - postal box) on an official source, which is clear. It distinguishes the tool from generic siblings by naming the specific domain (ECAC, Brazilian official sources). However, it doesn't specify the exact nature of the returned data (e.g., messages or receipts), so it's slightly below a perfect 5.

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. It mentions the context (official sources, paid via prepaid credit) but does not state when not to use it or compare with sibling tools. The usage is only implied by the description.

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?

Beyond the annotations, it discloses critical behavior: invoke runs uninstalled MCPs one-off without bloating the toolkit, requires owner/admin for writes, returns connect or checkout links for auth/payment, and describes how prompt links open without login. No contradiction with annotations exists.

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 dense and front-loaded with the core flow, then covers install-vs-invoke, permissions, and the prompt library. It is long, but for a 14-action compound tool, nearly every sentence contributes; only minor run-on phrasing and the Portuguese example feel extraneous.

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 tool with 14 actions and no output schema, the description covers the main flow, auth/payment edge cases, permanent vs one-off execution, write permissions, and the prompt-library sub-tools. It leaves some output formats and infrequent parameters unspecified, but is substantially 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?

With 23 parameters and 0% schema description coverage, the description must compensate. It explains key semantics for action, tool_id, arguments, prompt variables, and the core flow, but many parameters such as limit, immediate, tier_slug, conversation, cancel_reason, report_context, and request_details remain undocumented.

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 opens with a clear verb-resource pair: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then details the core action flow and differentiates itself from siblings by encompassing catalog search, MCP execution, installation, billing, and 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 gives explicit when-to-use guidance: 'prefer invoke for a single/occasional use,' 'Use install only to make an MCP PERMANENT,' and 'list_tools lists what is callable right now.' It also distinguishes report_bug, request_mcp, and subscribe/cancel from the main flow, making alternatives clear.

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 (expects side effects), destructiveHint=false, and idempotentHint=true. The description adds a behavioral guideline to include the conversation array for reproduction, which is useful. However, it does not disclose potential side effects (e.g., sending a report to a server) or other behavioral nuances beyond what annotations already imply.

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 consists of two concise sentences, front-loading the primary purpose before an actionable instruction. Every word earns its place, and there is no redundancy or vagueness. It efficiently conveys purpose and a key usage detail without unnecessary 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 tool with 3 parameters, no output schema, and annotations, the description provides adequate but not complete context. It explains the conversation parameter's purpose but does not clarify the 'context' field or expected behavior/return values. Still, for a bug-reporting tool, the description is sufficient for basic use, though missing details like response handling.

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 directly explains the 'conversation' parameter by instructing to include recent messages for reproduction, adding value beyond the schema's defaults. However, it leaves 'context' and 'message' unaddressed, though 'message' is self-explanatory. With 0% schema coverage, the description only partially compensates for parameter semantics.

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' plus resources 'bug, missing feature, or send feedback', clearly stating the tool's purpose. It distinguishes itself from sibling tools like 'authenticate' and 'marketplace' by focusing on user feedback. The additional instruction about the conversation array further clarifies the tool's 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 implies when to use this tool: when there is a bug, missing feature, or feedback to send. While it does not explicitly name alternatives or exclusions, no sibling tool serves a similar function, making the usage context clear. It could be enhanced by stating when not to use it, but the intent is straightforward.

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 the safety profile. The description adds only that it shows current platform and adapter versions, which is useful but not rich behavioral context; no return format or additional side-effect info is provided.

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, concise sentence fully states the tool's purpose with no redundancy or filler. 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 no-parameter, read-only informational tool, this description is complete. It states what the tool returns (versions) and is supported by strong annotations; no output schema is needed to understand the simple return value.

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 there are no semantics to clarify beyond the schema. A baseline of 4 is appropriate because the description cannot add parameter-level value when none exist.

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 clearly identifies the resource ('current MCP platform and adapter versions'). It distinguishes this tool from siblings like authenticate or connect by making its informational scope immediately obvious.

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?

For a simple read-only informational tool, the description gives clear context on what it does. It doesn't explicitly name alternatives, but no sibling appears to offer equivalent functionality, so the omission is not a significant gap.

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 aligns with annotations (readOnlyHint, idempotentHint) by framing the tool as a read-only status retriever. It adds value by detailing exactly which aspects of state are reported, making side effects (none) transparent.

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, concise sentence that front-loads the primary action ('Returns the current toolkit state') and efficiently lists the included details. No redundant or unnecessary 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 simplicity of the tool (no parameters, no output schema, read-only), the description is fully complete, specifying exactly what information is returned without requiring additional 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?

With zero parameters and 100% schema description coverage (empty schema), the description has no parameter semantics to explain. The baseline of 4 is appropriate, and the description's clarity compensates for the lack of 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: 'Returns the current toolkit state' and enumerates specific data points (installed MCPs, connection status, accounts, catalog tool counts). It distinguishes itself from sibling tools like 'authenticate' and 'connect' by focusing on inspection rather than actions.

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 by stating it returns current state, which makes it appropriate for status queries. However, it does not explicitly mention when not to use it or compare with alternatives, though the context of being an info-only tool is clear from the description and annotations.

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