Receita Federal: Radar (Habilitação Comércio Exterior)

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

The description discloses the authentication process (browser login, token copy) and the idempotent nature of the action. It clearly differentiates between permanent (config) and session-only (parameter) modes, which goes beyond the 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 concise yet thorough, structured logically with two clear usage scenarios. It avoids redundancy and efficiently conveys the necessary information 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?

Even without an output schema, the description provides enough context for an agent to understand both invocation modes and the expected outcomes (link vs. authentication). It covers the main use cases completely.

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 single optional parameter 'token' is explained in detail: it is a JWT used for session-only login, and omitting it yields a login link. This adds meaningful context to the schema, which only indicates a string field.

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: authenticate for IDE agents via browser login and token retrieval. It distinguishes itself from sibling tools by focusing on authentication and login 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 usage instructions: either add the token to server config for permanent access or pass it as a parameter for session-only login. It also explains the no-argument invocation to obtain the login link, leaving no ambiguity about when and how to use the 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by explaining the response structure (authenticated:true, empty pending[] when connected) and that connect_url is included when credentials are missing. This goes beyond annotations by clarifying behavior in different states.

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-loads the main purpose, and provides important conditional behavior concisely. Every word earns its place; no 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 no parameters and no output schema, the description covers the main aspects: what it returns and under what conditions. It describes the two states (all connected vs credentials missing) which is helpful for an agent. However, it could mention if there are any rate limits or permission requirements, but given the simplicity of the tool, this is fairly 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 0 parameters, so the baseline is 4. The description doesn't need to explain any parameters, and schema coverage is 100% (vacuously). The description does a good job explaining what the tool does without needing to describe 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 returns connection status and URLs, which distinguishes it from siblings like 'authenticate' and 'marketplace' by focusing on status/URLs. However, it could be slightly more explicit about the resource being 'connection status' as a specific resource, but it's clear enough.

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 connection status and get URLs), but it doesn't explicitly state when NOT to use it or name alternative tools. It provides functional context but lacks explicit exclusions or alternatives.

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 discloses significant behavioral traits beyond annotations: invoke runs MCPs even when not installed, writes (install/uninstall/subscribe/cancel) require workspace owner/admin, and invoke may return connect/checkout links requiring user action before retry. The description also notes that search/describe flag installation status. This comprehensively covers side effects and prerequisites, exceeding what annotations provide.

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 dense with information. It is front-loaded with the core flow and key distinctions, but the lack of structural breaks (paragraphs, bullets) makes it a wall of text. Given the tool's complexity (14+ actions), the length is justified, but it could be organized better for readability. Every sentence serves a purpose, so it earns the length, but structure could be improved.

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 complexity (23 parameters, no output schema), the description is remarkably complete. It covers the end-to-end flow, authorization requirements, error-handling links, the distinction between one-off and permanent installation, and even the separate prompt library feature. It doesn't detail every sub-action's parameters, but the core behaviors and edge cases are addressed, making it complete for practical use.

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 fully compensates by explaining the key parameters, especially 'action' with its many values and their semantics (search, describe, invoke, install, etc.). It also explains arguments, tool_id, mcp_id, and the prompt-related fields (prompt_slug, prompt_vars, etc.). While not every parameter is individually described, the ones that matter for core flows are covered, adding substantial meaning beyond the bare 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 what the tool does: it is the official marketplace for MCP/tools, both a catalog and a runtime. It explicitly defines its role as discovering, describing, invoking, and installing MCPs, and distinguishes itself from siblings by naming alternatives like report_bug and list_tools. The verb+resource combination is specific and comprehensive, making the purpose immediately clear.

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 guidance, including the core flow (search → describe → invoke) and clear differentiators: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It also explains when to use list_tools, the behavior for credentials (connect link) and payments (checkout link), and how to handle those cases. This is a model of when/when-not 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, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: it is hosted by the platform, requires no platform credentials, is pay-per-use, queries non-confidential citizen-accessible data, and involves LGPD compliance. This goes beyond annotations without contradicting 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 compact paragraph with four sentences, each adding distinct information: purpose, hosting/billing, data source/scope, and LGPD. There is slight redundancy ('consulta em fonte oficial' and 'fonte de órgãos oficiais'), but overall it is well-organized and front-loaded with the core 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?

The tool is simple (2 optional params, no output schema) and annotations cover safety. The description covers purpose, billing, and legal context, but it lacks specifics on expected output format/fields and does not explain how parameters relate to the query. Given no output schema, more detail on return values and parameter usage would improve completeness.

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 parameter meaning, but it does not mention CPF or CNPJ at all. The parameter names are self-explanatory to humans, but the description gives no guidance on usage, optionality, or constraints (e.g., whether one or both are needed). This is a significant gap for an agent relying on the description.

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: 'Receita Federal: Radar (Habilitação Comércio Exterior), consulta em fonte oficial.' It uses the specific verb 'consulta' (query) and identifies the resource (Receita Federal Radar). It is distinct from all sibling tools, which are generic platform utilities (authenticate, connect, etc.).

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: for querying official Brazilian sources as a citizen would. It also specifies operational conditions (no platform credentials, pay-per-query with prepaid credit), which helps the agent select it appropriately. However, it does not explicitly mention alternatives or exclusions, but the context is sufficient given the unrelated 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 cover idempotency, destructiveness, and read-only hints, reducing the burden on the description. The description adds useful context about including conversation history for reproduction, but it does not disclose what happens after submission (e.g., ticket creation, response format). This is adequate but not rich.

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 purpose and immediately followed by a targeted usage instruction. Every word adds value with no redundancy or filler.

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 low-complexity tool with only 3 parameters and no output schema. The description gives the core purpose and a key usage hint, but leaves out details about the 'context' parameter and any post-submission behavior. It is minimally sufficient but not fully 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?

Schema description coverage is 0%, so the description must explain parameters. It only addresses 'conversation' (the array for reproduction) and implicitly 'message' as the report content. The 'context' parameter remains completely unexplained, leaving a gap in parameter understanding.

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 explicit object types ('bug, missing feature, or feedback'), clearly conveying the tool's purpose. It distinguishes itself from sibling tools like 'show_version' or 'authenticate' by focusing on user feedback.

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 the tool (reporting bugs/missing features/feedback). It also gives a concrete usage instruction ('Include the conversation array with recent messages for reproduction'), but it does not explicitly exclude alternatives or state when not to use 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 destructiveHint false. The description adds useful context by specifying that the tool reports current platform and adapter versions. No contradictions or hidden side effects are evident, though the description does not detail the return format.

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 with no unnecessary words. It fully conveys the tool's purpose without repetition or filler.

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, idempotent version-reporting tool, the description and annotations are fully sufficient. No output schema exists, but the nature of the output ('platform and adapter versions') is clear enough for an agent to use the tool 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?

The tool has zero parameters, so the baseline is 4. The description adds no parameter semantics, but none are needed since the schema confirms an empty parameter set.

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 'Show the current MCP platform and adapter versions' with a specific verb and resource. It distinguishes this from sibling tools like toolkit_info by narrowing the output to version 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?

Usage context is implied: an agent would use this when it needs current version info. However, there is no explicit guidance on when to prefer this over sibling tools such as toolkit_info, nor any exclusion/alternative 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 establish readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context beyond these by specifying exactly what the return value covers (installed MCPs, connection status, accounts, catalog tool counts). This is especially valuable given there is no output schema.

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 core action and provides a clean, complete enumeration of the returned data. No filler or redundant information exists.

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 informational tool with strong annotations, the description fully covers what the tool returns and is sufficient for an agent to decide whether to call it. No additional context is needed.

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 accepts zero parameters, so the schema provides complete coverage and the description does not need to explain parameter meaning. Baseline 4 applies because there is no parameter documentation burden.

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 ('Returns') and a clearly defined resource ('current toolkit state'), enumerating distinct elements such as installed MCPs, connection status, connected accounts, and exposed catalog tool counts. This fully distinguishes it from sibling tools like show_version 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?

The description clearly implies when to use the tool: whenever an agent needs an overview of the current toolkit environment and per-MCP connection details. It does not explicitly mention alternatives or exclusions, but the context is unambiguous enough for a simple read-only state inspection tool.

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