ANVISA: Processo

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

The annotations already declare the tool as read-only, idempotent, non-destructive, and not open-world. The description adds context about the data being the same as available to citizens and not confidential, which is useful for compliance. However, it doesn't add much about behavioral traits that aren't already covered by annotations. It mentions the commercial model (prepaid credits) which is a behavioral trait. Overall, it's a bit beyond what annotations say, but not extensively. 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 a bit long but provides relevant legal and commercial context. It front-loads the purpose ('ANVISA: Processo, consulta em fonte oficial') and then adds context about hosting, credits, and LGPD. For an AI agent, this context is useful for legal compliance decisions. It could be more concise, but the structure is logical.

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 relatively simple: a query with 3 optional parameters. The annotations cover safety (readOnly) and idempotency. The description adds legal context (LGPD, data control). However, it lacks information about the output format or any specifics about the query parameters (e.g., are they mutually exclusive? do they accept wildcards?). Given the simplicity of the tool, the description is mostly complete, but the absence of output schema and lack of parameter documentation leave 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?

Schema coverage is 0%, meaning the description does not explain any of the three parameters (protocolo, expediente, numero_processo). However, the parameter names are in Portuguese and are relatively self-explanatory to a Portuguese speaker: protocol number, expediente (docket), and process number. The baseline for 0 params is 4, but with 3 params and 0% coverage, the description should compensate. It does not elaborate on when to use which parameter or if any are preferred. The names are clear but the description adds no additional meaning beyond what the schema field names imply, so a score of 3 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 queries ANVISA processes from an official source. It is somewhat generic ('consulta') but the specificity of 'Processo' with 'fonte oficial' ties it to the ANVISA domain. It lacks an explicit comparison to sibling tools, but the name ('anvisa_processo_consultar') is quite specific and the description accurately reflects the action of querying process information. A minor deduction because it could be more explicit about what type of 'processo' (administrative, sanitary, etc.) but the domain context makes it 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 mentions the platform is hosted, uses prepaid credits, and that the client is the data controller (LGPD context). However, it doesn't explicitly state when to choose this tool over alternatives or exclude any use cases. The sibling list includes 'connect', 'marketplace' which might be alternatives for accessing data, but the description doesn't provide a comparison. It implies usage context but lacks explicit guidance on when to use this tool vs others.

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 important behavioral traits, such as the permanent vs. session-limited nature of tokens and that calling with no arguments returns a link. This adds context beyond the annotation hints (e.g., idempotentHint=true) and explains side effects, though it omits potential error handling or rate-limit information.

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 contains all necessary information but is presented as a run-on, slightly disorganized block. Key points like 'Best:' and 'Or paste it here' could be structured with clearer separation and front-loading, but no sentence is wasted.

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 all facets of usage: authentication flow, token handling, both invocation patterns, and the permanent vs. session distinction. It adequately equips an agent to use the tool correctly without 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?

Despite the schema having no property descriptions, the description thoroughly explains the optional 'token' parameter, its expected format (JWT), and the effect of omitting it. This fully compensates for the 0% schema coverage by providing essential semantic meaning.

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 authenticates IDE agents via browser login and token retrieval, using specific verbs like 'log in' and 'copy the access token.' It uniquely identifies the tool's function and distinguishes between the two login modes, making its purpose unmistakable.

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, step-by-step usage instructions, including two alternative methods (permanent config token vs. session-only token) and the exact payload format. However, it does not compare this tool to its siblings or explicitly state when to prefer an alternative, so it doesn't reach a 5.

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, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds meaningful behavioral context by specifying the two return scenarios (authenticated:true with empty pending[], or connect_url for toolkit and per-install URLs). This explains what the agent can expect in different states, going 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 two sentences, front-loaded with the core purpose ('Returns connection status and URLs'), followed by clarifying scenarios. Every sentence adds value, 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?

Despite having no output schema, the description adequately conveys what the tool returns and under what conditions. It covers the main scenarios and the fields returned (authenticated, pending, connect_url). Given the simplicity of the tool (no parameters) and the annotations, the description is reasonably complete. However, it could be slightly more explicit about the meaning of 'providers' or the overall purpose of the status check, hence a 4 rather than 5.

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 coverage is trivially 100%. Per the baseline for 0 parameters, a score of 4 is appropriate. The description does not need to explain parameters since none exist, and it correctly focuses on return behavior.

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, and explains the two distinct output states (all providers connected vs missing credentials). This is specific and distinguishes it from sibling tools like authenticate which likely initiates connections, and report_bug or show_version which have 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 description implies usage by describing when to expect different outputs (when all providers are connected vs credentials missing), but it does not explicitly compare with alternatives or state when not to use this tool. It leaves the agent to infer it should be called to check connection status, without guidance on when authenticate or other tools might be more appropriate.

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 richly discloses behaviors beyond the sparse annotations: invoke runs uninstalled MCPs one-off without bloating the toolkit, auth failures return connect links, empty wallets return checkout links, writes require workspace owner/admin, and prompt links open without login. No contradiction with annotations is present.

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 densely informative, front-loaded with the core marketplace purpose and workflow. Every sentence adds meaningful context, though the single-paragraph structure could be more scannable with bullets. The length is justified by the tool's breadth.

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 and lack of output schema, the description is remarkably complete: it covers the full action flow, permissions, auth and payment edge cases, installed vs installed_in_workspace flags, permanent vs one-off execution, and the separate prompt-library domain. This is sufficient for an agent to select and invoke the tool correctly in most scenarios.

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 explain the 23 parameters, and it does substantial work: it maps action values to workflows, explains mcp_id/tool_id selection, arguments for invoke, and prompt-related parameters. However, several parameters such as limit, immediate, tier_slug, conversation, cancel_reason, and request_details are not individually addressed, leaving some gaps.

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 official mcp.ai marketplace and catalog/runner for MCPs, then enumerates its concrete functions: search, describe, invoke, install, list_tools, and prompt-library operations. This goes beyond a vague or tautological purpose and distinguishes marketplace as a multi-action discovery and execution hub.

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: use invoke for one-off/occasional execution, use install to make an MCP permanent, and use list_tools to see what is currently callable. It also lays out the core search → describe → invoke flow and directs users to request_mcp when nothing fits.

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 mentions 'report' which implies a write action, but it does not explicitly state side effects, such as creating a ticket or sending an email. With only minimal annotations (idempotentHint true, destructiveHint false), the description carries some burden but remains incomplete regarding the actual effect.

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 (two sentences), directly addresses the tool's function, and includes a specific call to action regarding the conversation parameter. No unnecessary words 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?

The description lacks details about the tool's output (e.g., a confirmation or ticket ID), whether it is asynchronous, or any required permissions. It covers the basic 'how to use' but omits post-report behavior, making it only partially complete for the user.

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 defines three parameters (context, message, conversation) with no individual descriptions. The description only explains 'conversation' as an array for reproduction, leaving 'context' and 'message' undefined. This is insufficient given the low schema coverage (0% with descriptions).

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: reporting bugs, missing features, or sending feedback. The verb 'report' is specific and the direct mention of these use cases makes it distinct from sibling tools like authenticate or 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 advises including the conversation array for reproduction, which is a practical usage hint. However, it does not explicitly differentiate from alternatives (though none exist for this purpose in the sibling list) or specify when to use this tool over others.

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 clearly indicate read-only, idempotent, non-destructive behavior. The description adds the specific scope (MCP platform and adapter versions) which is useful context beyond the generic 'show version'. No 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 a single, clear sentence with no wasted words. It is appropriately minimal for a simple informational tool.

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 simple output, the description is sufficient. It doesn't detail the exact output format, but given no output schema and the simple nature, it provides enough context. It could mention usage in troubleshooting or connection diagnostics, but not essential.

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 schema already fully describes inputs. The description doesn't need to add parameter semantics. Base score of 3 is appropriate given no 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 it shows current MCP platform and adapter versions. It may overlap with sibling 'toolkit_info' but the specific focus on versions differentiates it somewhat. It uses a specific verb (show) and resource (MCP platform and adapter versions).

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 a simple informational query but does not explain when to choose this over 'toolkit_info' or other sibling tools. No explicit when-to-use or exclusions.

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, which inform the agent that this is a safe, non-mutating operation. The description adds value by specifying exactly what information is returned (installed MCPs, connection status, accounts, catalog tool counts), which is beyond the annotations. However, it doesn't disclose any additional behavioral traits like potential latency or whether it requires network calls, so a score of 3 is warranted as it adds some context but not extensive.

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 sentence that is clear and front-loaded with the verb 'Returns', immediately stating the purpose. It is concise and provides essential information without unnecessary details. It earns a 4 because it is efficient and well-structured, though it could be slightly more compact by trimming 'currently' and 'each one' without losing meaning, but it's nearly ideal.

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 this tool has no parameters, no output schema, and is marked with read-only and idempotent annotations, the description is fairly complete. It outlines the key aspects of the tool's output: installed MCPs, connection status, accounts, and tool counts. It doesn't mention details like whether the state is live or cached, but for a simple info tool, this is sufficient. The sibling tools 'authenticate' and 'connect' are action-oriented, so this description stands on its own. A score of 4 is justified.

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, the description doesn't need to explain parameters, and the schema coverage is 100% (trivially, as there are no parameters). The description adds contextual meaning by indicating what the returned state includes, which is helpful for the agent to understand the purpose without any input. Since there are no parameters, a baseline of 4 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 what the tool does: it returns the current toolkit state, listing installed MCPs, their connection status, connected accounts, and the count of catalog tools per MCP. It is specific and uses a clear verb ('Returns'), and it distinguishes itself from sibling tools like 'authenticate' and 'connect' by focusing on state inspection rather than actions. It loses one point because it doesn't explicitly differentiate from 'show_version' or 'marketplace', but the content is distinct 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 that this tool is for inspecting the toolkit's state, likely useful before or after connecting or authenticating, but it does not explicitly state when to use it or when not to use it. It doesn't mention alternatives or exclusions, so it provides only implicit guidance. A score of 3 is appropriate for implied usage without explicit context.

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