Conselho Regional de Odontologia MS: Cadastro

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

The description explains behavioral outcomes (permanent vs. session-only login) and does not contradict annotations. However, it does not explicitly state side effects like whether the tool mutates server state or requires specific permissions, though annotations hint at idempotency. The description adds value beyond annotations by clarifying token 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 well-organized but somewhat verbose, with a conversational tone. It front-loads the main purpose and then explains usage. Could be slightly more concise but every sentence adds value.

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 parameter structure and no output schema, the description sufficiently covers usage. It mentions both calling modes and the token format, though it does not explicitly describe the response or return value. This is a minor gap, but overall complete enough for the tool's simplicity.

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 zero schema description coverage, the description fully explains the 'token' parameter: it expects a JWT for session login, and no arguments returns a link. This provides complete semantic meaning for all 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: authentication for IDE agents, involving browser login and token retrieval. It distinguishes itself from siblings by focusing on authentication, while other tools like 'connect' or 'marketplace' serve different functions.

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?

Explicitly provides two usage modes: permanent via config header (recommended) and session-only by pasting a token. It also specifies how to call the tool with a token or without arguments. This gives clear when-to-use guidance and 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds meaningful behavioral detail by specifying the exact response shape for both success and missing-credential cases, including fields like authenticated, pending[], connect_url, and per-install URLs. This goes beyond the 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 only two sentences: the first front-loads the core purpose, and the second elaborates on the two conditional outcomes. There is no redundant or filler wording; every sentence 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 0-parameter read-only tool with no output schema, the description covers the two main outcomes well. However, it does not explicitly address behavior for a partial-connection state (e.g., some providers connected, some missing), which could leave the agent uncertain about intermediate cases.

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 (100% coverage with no properties). The baseline for 0 params is 4, and the description appropriately includes no parameter information since none exist to explain.

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 the specific verb 'Returns' and identifies the resource as 'connection status and URLs,' clearly distinguishing this from sibling tools like 'authenticate' which perform actions. It also explicitly outlines the two key output states, making its purpose unambiguous.

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—to retrieve connection status—and explains the two relevant scenarios ('all providers connected' vs 'credentials missing'). However, it does not explicitly state when not to use it or name alternative tools, so it lacks explicit 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's a safe read-only operation. The description adds context about the data being public ('não é dado sigiloso') and the payment model, but doesn't explain side-effects like credit deduction or any rate-limiting behavior. It adds value beyond annotations (payment, data sensitivity) but does not fully describe operational behavior.

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 reasonably concise (2-3 sentences) but includes legal disclaimers (LGPD) and payment terms that are not operationally relevant. It is not badly structured, but the most actionable information (how to query, what input is needed) is mixed with general context.

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 provides context about the data source and legal aspects but lacks specifics about input format, expected output, or error conditions. For a simple one-parameter query tool, it is somewhat complete, but the missing parameter semantics and output description leave 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?

The schema has one parameter (inscricao) with 0% coverage in the description. The word 'Cadastro' hints it's a registration number, but no format, example, or constraints are provided. Since the schema gives no description, the tool description should compensate but does not explicitly explain the parameter.

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 this tool consults registration data from the Regional Council of Dentistry of Mato Grosso do Sul (CRO-MS) from official sources. It specifies the main action ('consulta') and the subject matter (registration in an official body), though it could be more explicit about the exact type of information returned.

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 prepaid credit and LGPD compliance but provides no practical usage instructions—when to use this tool versus alternatives, how payment works, or what constitutes a valid query. No sibling tool distinction is made. It lacks guidance on how an agent should invoke it correctly.

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 goes far beyond the sparse annotations by disclosing side effects: invoke runs a tool one-off without installing it, missing credentials return a connect link, empty wallets return a checkout/top-up link, writes require workspace owner/admin, and publish_prompt creates a shareable link opening without login. There is no contradiction with 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 one long, dense paragraph rather than structured bullets, but almost every sentence adds necessary operational detail for a 14-action tool. It is front-loaded with the primary purpose and core flow before diving into edge cases and the prompt library. Slightly better organization would make it a 5.

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 very high complexity (23 params, no output schema, minimal annotations), the description covers an impressive amount: core discovery/run flow, one-off vs. permanent install behavior, auth and payment edge cases, permission requirements, and the separate prompt library. It misses details on a few actions and parameters (resume, immediate, output shapes), which prevents full 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?

With 0% schema description coverage across 23 parameters, the description carries a heavy burden and compensates well for the central parameters: it explains action's enum values, tool_id selection, mcp_id context, prompt_slug usage, and the meaning of list_tools/invoke/install. However, several parameters (arguments, immediate, tier_slug, conversation, prompt_vars, prompt_targets) remain semantically unexplained, so the compensation is strong but not complete.

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 specific, self-contained definition: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then enumerates the key sub-flows (search, describe, invoke, install) and even the prompt-library feature, making the tool's multi-purpose scope clear and differentiating it from the more specific 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?

Usage guidance is explicit and prescriptive: it spells out the core flow ('action=search discovers → describe returns profile → invoke RUNS'), and gives direct preference rules like 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also names alternatives for unmet needs via request_mcp and explains when to use the prompt-library actions.

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 idempotent and non-destructive behavior; the description adds context by explaining the conversation array is for reproduction, which hints at how the tool uses data. It doesn't describe side effects or confirmation, but given annotations cover safety, a moderate score 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?

Two concise sentences, front-loaded with purpose and one vital usage note. Every word earns its place with no redundancy or irrelevant 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 3-parameter tool with annotations, the description gives enough to understand intent and one key parameter, but the conversation type mismatch and lack of explicit description for message/context create gaps. Without an output schema, more parameter clarity would be expected, so completeness is only moderate.

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 must compensate. It defines the purpose of 'conversation' but mislabels it as an array while the schema declares a string, causing potential confusion. It entirely omits 'message' (required) and 'context', leaving meaning lacking. This fails to compensate for low schema coverage.

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 reports bugs, missing features, or feedback, which is distinct from sibling tools like connect or marketplace. It uses a specific verb (report/send) and resource (bug/feedback), making the purpose unambiguous.

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 clear guidance to include the conversation array for reproduction, establishing context for use. However, it lacks explicit 'when not to use' or alternative tool recommendations, missing the highest bar. Sibling tools are unrelated, so exclusion would be helpful but isn't critical.

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 the specific scope (MCP platform and adapter versions) not present in annotations, but it does not introduce any additional behavioral traits. It aligns with annotations and adds slight 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?

The description is a single, concise sentence that fully states the purpose without any filler or redundant information. It earns its place entirely.

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, the description is complete. No output schema exists, but the tool is simple enough that the return value is self-evident from the description. 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 has zero parameters, so baseline is 4. The description needs no parameter explanation. It does not add anything beyond the schema, but there is nothing to add.

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 a clear resource ('current MCP platform and adapter versions'), which fully distinguishes it from sibling tools like authenticate or connect. It is immediately obvious 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 usage by its clearly stated purpose, but it does not explicitly state when to use this tool versus alternatives or provide any exclusions. Since there are no related tools for version checks, the purpose itself is sufficient context, but no explicit guidance is given.

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 the tool read-only, idempotent, and non-destructive. The description adds valuable context by specifying exactly what state is returned (MCPs, connection status, accounts, catalog counts), which helps the agent understand the return contents 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 a single, front-loaded sentence that states the main action first and then lists the components of the returned state. Every part is informative 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 simple, parameterless, read-only information tool, the description fully conveys what the agent will receive. No output schema is needed because the enumerated return components are sufficiently described. Sibling tools do not introduce ambiguity requiring further elaboration.

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 works seamlessly with an empty schema, and there are no parameter semantics to document.

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') with enumerated details (installed MCPs, connection status, accounts, catalog tool counts). It distinguishes itself from siblings like show_version and connect by focusing on state inspection.

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 the tool should be used when an agent needs an overview of the toolkit's MCP installations and connections. It does not explicitly state alternatives or exclusions, but sibling tools are clearly different in purpose, making the usage context reasonably clear.

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