SUSEP: Corretores

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

Annotations already declare idempotentHint=true and destructiveHint=false, setting a safety baseline. The description adds context about permanent vs. session login modes, but doesn't disclose potential side effects like token validation failures or session expiration. It complements 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 concise three-sentence paragraph that front-loads the purpose and seamlessly explains two usage paths. Every sentence adds value, with no redundant information 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 simple single-parameter tool, the description covers the essential workflows (permanent vs. session) and call patterns. It doesn't elaborate on response handling, but the lack of an output schema reduces that need. The context is sufficient for an agent to invoke and understand the tool's function.

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 compensates for the 0% schema coverage by explaining the token parameter: it's a JWT for session login, and omitting it triggers a link generation. However, it doesn't specify token format details beyond '<jwt>', leaving some ambiguity for agents.

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 explicitly states the tool is for authenticating MCP.AI IDE agents, describing browser login and token usage. It distinctively focuses on authentication, separating it from siblings like connect or marketplace. The verb 'authenticate' and resource (access token) are clear and specific.

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 provides clear usage guidance: either add token to server config for permanent connection or paste it for session-only login, with explicit instructions on calling with/without the token argument. While it doesn't mention when NOT to use it, the scenarios are clearly delineated and distinct from sibling tools.

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, destructiveHint=false, so the safety profile is clear. The description adds what it returns (authenticated, pending, URLs) but doesn't go deeper into side effects or rate limits. It adds some value but is not rich, so a 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, front-loaded with the main purpose, and includes necessary conditional details. Every sentence earns its place with 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 zero-parameter, read-only status tool with no output schema, the description covers the main behavior and key conditional returns. It could mention what 'per-install URLs' represent or clarify 'providers', but it's adequate for the scope. Sibling tools are distinct enough, so no cross-reference 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 input schema is empty (0 parameters), and schema coverage is 100% as nothing to document. The description explains the behavior and return values, which is sufficient. Baseline for 0 params is 4, so this is correct.

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: returning connection status and URLs. It specifies the verb ('Returns') and resource ('connection status and URLs'), and distinctly separates it from siblings like authenticate or report_bug by focusing on connection state.

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 conditional behavior based on connection state (all providers connected vs credentials missing), which implicitly tells when to use it. However, it does not explicitly mention when not to use it or compare with alternatives (e.g., authenticate). The usage context is implied but not fully explicit.

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 (which signal a non-read-only, mutating tool), the description discloses meaningful behavior: invoke runs one-off without installing, writes require workspace owner/admin, and login/checkout returns special links. Loses a point for the language confusion (the mixed Portuguese 'pontualmente'), lack of failure-mode discussion, and no rate-limit context.

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 dense wall of ~400 words with no paragraph breaks, bullets, or hierarchy. The exact 'when to use' guidance is buried mid-paragraph, and typos like 'MPp' and the Portuguese interjection 'pontualmente' add noise. The core search/describe flow could be a clean few lines but is packed in with billing and prompt-library minutiae.

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 of this complexity (14 actions, 2 subsystems, auth/payment edge cases), the description covers a remarkable amount of the feature surface: the core search→describe→invoke flow, install vs invoke semantics, auth requirements, payment links, list_tools, and the prompt library. Gaps exist around return values and specific error scenarios, but overall the coverage is strong.

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 coverage and 23 parameters, the description carries the full burden here, and while it extensively explains the action enum values (search/describe/invoke/install/etc.), it completely ignores crucial parameters. The JSON-string params (arguments, prompt_vars, conversation) get no format hints, and most of the prompt_*/cancel_* params are undefined despite their non-obvious defaults and purposes.

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 the tool as the mcp.ai marketplace catalog and execution engine, with a concrete core flow (search → describe → invoke). It uses specific verbs and describes the resource adequately. However, the purpose competes with a massive amount of tangential detail (billing, prompt library, bug reporting), which dilutes the central definition.

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 differentiation: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use' and covers credential/payment edge cases. However, the guidance is embedded in a stream-of-consciousness block rather than structured, and no sibling tools are explicitly named as 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 annotations already indicate a non-read-only, non-destructive, idempotent operation. The description adds the useful reproduction requirement, but it does not disclose submission behavior, output, or any prerequisites beyond the conversation data.

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 filler. Every word contributes to understanding the tool's purpose and the primary invocation 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?

For a simple reporting tool with annotations, the description is adequate for basic use, but the 0% schema coverage and missing output schema mean more parameter guidance is needed. The optional 'context' field and conversation format remain under-specified.

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 carries the burden for explaining parameters. It partly clarifies the message and conversation fields, but it leaves 'context' unexplained and does not specify that the conversation should be a JSON string, creating ambiguity.

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') and clearly identifies the target categories: bug, missing feature, or feedback. It is unambiguous and distinct from the unrelated sibling tools.

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 clearly states when to use the tool—for reporting bugs, missing features, or feedback—and instructs the agent to include the conversation for reproduction. It does not explicitly name alternatives or exclusions, but no sibling tool competes for this purpose.

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 convey that this is a read-only, idempotent, non-destructive operation. The description adds no behavior beyond the stated purpose, such as output format or whether authentication is required, but it does not contradict 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 a single, front-loaded, 12-word sentence that communicates the tool's entire purpose with no filler or 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 zero-parameter, no-output-schema, simple version-display tool, the description is fully adequate. It identifies what will be shown (MCP platform and adapter versions) and no additional constraints or return-value details are necessary.

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 schema coverage is 100%, so there is no parameter-semantic burden on the description. The baseline of 4 applies because no parameter explanation is 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 uses a specific verb ('Show') and identifies the exact resource being returned ('current MCP platform and adapter versions'). This clearly differentiates it from sibling tools like authenticate or report_bug, which serve entirely 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?

The intended use is implied: call this tool whenever current platform/adapter version information is needed. However, the description does not explicitly state when to use it versus alternatives such as toolkit_info, nor does it mention any exclusions or prerequisites.

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 indicate read-only, idempotent, non-destructive behavior. The description adds meaningful context beyond those hints: it is credential-free, prepaid, returns non-confidential public data, and clarifies data-controller responsibilities. It does not contradict 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 fairly compact and front-loaded with the core purpose. Some redundancy exists, such as repeating 'fonte oficial' and 'órgãos oficiais', but overall each sentence contributes useful context without excessive length.

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 there is no output schema and the parameter schema is minimal, the description should explain how to invoke the query (e.g., using CPF or CNPJ) and what the response contains. It only offers general legal/commercial context, leaving a significant operational gap for 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?

The input schema has two completely undocumented parameters ('cpf', 'cnpj') with 0% schema description coverage, and the description never mentions them. It fails to explain what these identifiers are for, whether one or both should be provided, or any format constraints, leaving the agent without necessary 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 opens with 'SUSEP: Corretores, consulta em fonte oficial', which clearly states the action (consulta) and resource (SUSEP corretores). It also distinguishes the tool from the generic sibling tools by emphasizing official-source data and a query action.

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 practical usage context: it is hosted on the platform, requires no platform credentials, and is paid per consultation with prepaid credit. It also notes LGPD compliance responsibilities, implying appropriate legitimate-purpose usage, though it does not explicitly mention alternative tools or exclusionary cases.

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, destructiveHint=false, so the agent knows it's safe. The description adds the specific content returned (connection status, accounts, catalog counts) which is useful behavioral context. However, it doesn't mention any potential complexities, rate limits, or caveats about freshness/staleness. With annotations covering the safety profile, the added value is moderate, so a 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 a single, tightly written sentence that front-loads the verb and clearly enumerates the return content. No filler or redundancy—every word adds information about what the tool does.

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 has no parameters, no output schema, and simple state-returning behavior, the description is fully sufficient. It enumerates the types of information returned, which is all an agent needs to understand invocation and expected output. No additional context is necessary.

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 zero parameters)Skip, so per the rubric baseline is 4. The schema is empty with 100% coverage (trivially). The description doesn't need to explain parameters because there are none, but it also doesn't add semantics beyond what's already implied—still, a baseline of 4 is deserved.

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 clearly names the resource ('current toolkit state') and enumerates the contents: installed MCPs, connection status, accounts, and catalog tool counts. It distinguishes itself from sibling tools like authenticate/connect which perform actions, whereas this is an informational query.

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 this tool would be used: to inspect the toolkit state. It doesn't explicitly state 'use instead of X' but the nature of the tool and the sibling list (authenticate, connect, etc.) make the context obvious. However, it lacks explicit guidance on when not to use it, so it misses a full 5.

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