Light: Download via CEP

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

Annotations indicate non-readonly, idempotent, non-destructive. The description adds valuable context: browser login steps, token permanence (non-expiring vs session-only), and behavior of no-args invocation (returns link). No contradictions 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 a single, long sentence but flows logically with structure ('Best:' vs 'Or'). It front-loads the core idea and avoids redundancy, though it could be slightly more concise without losing meaning.

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 simple input schema and lack of output schema, the description covers the essential aspects: auth mechanism, parameter semantics, and two usage modes. It does not detail return values or error handling, but for an auth tool this is acceptable.

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 schema has only an optional token parameter with no description. The tool description fully compensates: it clarifies that token is a JWT for session-only login, and that calling with no args returns the login link. This entirely clarifies parameter usage and optionality.

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 to the MCP server via browser login and token exchange. It distinguishes from siblings by describing specific auth flows (permanent config vs session-only), but does not explicitly name alternatives like 'connect'.

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 guidance: call with no args to get a login link, or with a token for session-only login. It also explains the permanent alternative (adding to server config). However, it lacks a direct comparison to sibling tools or exclusions like 'when not to 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 mark it as read-only and idempotent, which the description doesn't contradict. It adds context about response variations (authenticated:true with empty pending[] vs. connect_url when credentials missing), which is valuable beyond the annotations. No annotation contradiction.

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 brief, two sentences, and directly front-loads the main purpose. Every sentence adds value (returns status, conditional behavior). 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?

Given the tool's simplicity (0 params, no output schema), the description is nearly complete. It explains the two possible return states but doesn't detail the structure of connect_url or per-install URLs; however, that might be unnecessary. For a zero-param tool, this is adequate.

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 0 parameters, and schema coverage is 100% (vacuously high). So the baseline is 4. The description explains what the response contains, but since there are no params, the description's job is not about params. The high coverage means full marks baseline.

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?

Description clearly states the tool returns connection status and URLs. It distinguishes itself from siblings by describing the status output, but it doesn't explicitly name alternatives like the TDQS high example.

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 it—when checking connection status—but doesn't state when not to use it or explicitly mention alternatives like 'authenticate' or 'toolkit_info'. Context is clear but exclusion isn't 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?

The description adds important behavioral details beyond annotations: each query consumes prepaid credits, no authentication needed, data is from official public sources and not confidential, and LGPD compliance. These are not present in the readOnly/idempotent annotations and enrich understanding of side effects and constraints.

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 moderately verbose with repetition (e.g., 'consulta em fonte oficial' and 'Consulta informação de fontes e órgãos oficiais brasileiros'). It could be tightened without losing meaning, but it is still readable and not overly lengthy.

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 description explains the data source and payment model but omits crucial context about the optional parameters (cpf, cnpj, instalacao) and does not mention response format or possible errors. For a simple query tool, this leaves significant 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?

The description only mentions 'CEP' as the query parameter, but the schema lists four params (cep, cpf, cnpj, instalacao) with no explanations. It does not clarify the purpose or usage of cpf, cnpj, or instalacao, leaving them completely ambiguous.

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 is a query tool for CEP data from official sources, using 'consulta em fonte oficial' and 'consulta informação de fontes e órgãos oficiais'. This distinguishes it from sibling tools like authenticate or connect, though 'Download' in the name adds slight ambiguity.

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 usage context: requires prepaid credits ('pague por consulta com crédito pré-pago') and no platform credentials ('sem credenciais da plataforma'). This hints when to use it, but does not explicitly compare to alternative tools or state when to avoid 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?

The description adds significant behavioral detail beyond annotations: invoke runs tools even if not installed, returns connect/auth links for missing credentials, and provides purchase links for insufficient wallet balance. It explains that install makes MCPs permanent while invoke is one-off, and describes the publish_prompt behavior (shareable link, no login). No contradictions with annotations; instead, it enriches the minimal annotation 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 dense single paragraph containing extensive information delivered in a logical flow. While every sentence adds value and there's minimal fluff, the lack of formatting (bullets, headers) makes it harder to scan. It respects the reader's time by front-loading the purpose and core flow early, but the sheer length prevents a higher score for conciseness.

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 params, 14 actions, two major feature sets), the description is remarkably complete. It covers the discovery→inspect→run pipeline, explains permission requirements, handles edge cases like retry after user interaction, and distinguishes between MCP tools and prompt library features. The lack of an output schema is mitigated by describing expected outputs (connect links, checkout links, shareable links) in enough detail for an agent to proceed.

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 core action parameter values (search, describe, install, invoke, etc.) and their purpose. It clarifies tool_id, mcp_id, prompt_vars via {{variables}}, and other parameters conceptually. However, with 23 parameters, several (like limit, query, conversation, report_context) remain unexplained, and the description doesn't systematically map to each parameter. Still, it provides enough semantic meaning for the most critical 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 is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It specifies the resource (MCPs, prompts) and actions (search, describe, invoke, install), and differentiates from siblings by being the central hub for discovering and executing MCPs. The core flow is explicitly outlined, 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?

Excellent guidance is provided on when to use each action: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It covers alternatives (e.g., 'if nothing fits' use request_mcp), permission requirements ('Writes... require workspace owner/admin'), and error handling (e.g., connect link, checkout link, and retry). The description also distinguishes between MCP search/use and the prompt library, offering clear context.

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 the tool is not read-only (readOnlyHint:false) and non-destructive (destructiveHint:false) with idempotentHint:true. The description adds minimal behavioral detail beyond what annotations provide. It does not clarify what happens when reporting (e.g., whether a network request is sent, if a report is created), nor does it elaborate on side effects. The mention of 'conversation array' is more of a parameter hint than behavioral 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?

The description is extremely concise—two sentences that efficiently convey the tool's purpose and a key usage hint. It front-loads the primary verb and object, with no wasted words. It earns a top score for its brevity and 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?

Given the tool's simplicity (3 flat parameters, no output schema), the description covers the core purpose and one parameter's use. However, it omits any mention of what happens after reporting (e.g., no response message status) or any prerequisites. It is adequate for a basic tool but leaves room for improvement by clarifying expected outcomes or side effects.

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 must compensate for parameter understanding. It does clarify the 'conversation' parameter by instructing to include 'the conversation array with recent messages for reproduction', which helps if users know it's a JSON string. However, it provides no insight into 'message' or 'context' parameters, leaving their purposes unclear. The description partially bridges the gap but insufficiently.

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: 'Report a bug, missing feature, or send feedback.' It uses a specific verb ('Report') and resource (bug/missing feature/feedback), making it easy to understand its function and distinguish from siblings like 'authenticate' or 'marketplace'. There's no ambiguity about what the 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 implies when to use the tool (when you encounter a bug or have feedback) but does not explicitly compare with alternatives or provide exclusions. The instruction to 'Include the conversation array' gives some context but is more about how to use rather than when. It's enough to infer usage but lacks explicit 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?

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it shows platform and adapter versions, which provides context beyond the annotations, but it does not disclose the return format, whether authentication is needed, or any other behavioral traits such as response speed or error handling.

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, efficient sentence with no fluff or redundancy. Every word contributes to the tool's purpose, making it highly concise and easy to parse.

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 params, no output schema), a brief description is mostly sufficient. However, it could be slightly more complete by hinting at the return structure (e.g., a JSON object with platform and adapter fields) to help the agent anticipate the result. Still, the current description is adequate for a version-information 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, and the schema is empty, so there is nothing to explain. The baseline for 0 params is 4, and the description adds no parameter-specific information, but that is not a deficiency given the absence 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 uses a specific verb ('Show') and clearly identifies the resource ('current MCP platform and adapter versions'), making the tool's purpose unambiguous. It is distinct from sibling tools like 'toolkit_info' which likely covers broader information, so there is no confusion about its scope.

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 guidance is provided on when to use this tool versus alternatives such as 'toolkit_info' or 'connect'. The description does not mention any prerequisites, exclusions, or context in which this tool is appropriate, leaving the agent to infer usage from the name alone.

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 description carries low safety disclosure burden. It adds valuable context about the return content (installed MCPs, connection status, accounts, catalog tool counts), which is essential since no output schema 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, front-loaded sentence that efficiently enumerates the return contents without redundancy. Every word contributes to understanding.

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 tool with no output schema, the description fully specifies what the response contains. No further context is necessary for an agent to select and 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?

There are zero parameters, so the baseline is 4. The description correctly omits parameter details, and schema coverage is trivially 100%.

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 specifies the resource ('current toolkit state') and the content scope (installed MCPs, connection status, accounts, catalog tool counts). This fully distinguishes it from sibling tools like connect or show_version.

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 use when an overview of toolkit state is needed. It does not explicitly list alternatives or exclusions, but the context is clear enough for a zero-parameter info tool, and it stands apart from sibling actions.

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