Cemig: Download de Contas para Profissionais

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

Annotations indicate idempotentHint=true and destructiveHint=false. The description adds context about the authentication flow (browser login, token persistence) and the optionality of arguments, which is beyond annotations. It doesn't deeply describe the behavior of the token validation or session lifecycle, but given annotations cover safety, this is adequate. No contradiction found.

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 paragraph but contains dense, helpful information. It front-loads the audience (IDE agents) and main action (log in in the browser, copy token), then elaborates on the two options. It could be slightly more structured (e.g., bullet points), but it remains concise with no filler words, earning a 4.

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 with one optional parameter, no output schema, and no nested objects. The description covers the two usage modes (config-based permanent and session-only), explains the parameter semantics, and gives context about the token format (JWT). For this complexity, it is nearly complete; it could mention expected return values (e.g., success/failure response) but that is minor.

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 0% description coverage and only declares 'token' as a string with no description. The description compensates by explaining the token parameter: it should be a JWT pasted by the user for session-only login, and that omitting it returns a login link. This adds significant meaning beyond the schema, upgrading from baseline 3 to 4, though it could clarify the token format (e.g., JWT) more explicitly.

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's purpose: to authenticate IDE agents by logging in via browser or providing a token. It specifies the resource (authentication) and the action (authenticate), and distinguishes itself from siblings by focusing on the login mechanism, though it does not explicitly name alternatives. It reads as a clear purpose statement.

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 concrete usage instructions: recommend adding a bearer token to the server config for permanent access, or calling with a token for session-only login, or calling with no args to get the login link. It clearly states when to use the tool (when needing to authenticate) and the modes of invocation, though it doesn't explicitly mention when not to use it compared to 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, idempotentHint, and destructiveHint, covering safety. The description adds valuable behavioral detail about conditional responses (authenticated:true with empty pending[] vs. connect_url), which goes beyond annotations and helps the agent predict tool 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 two sentences, front-loaded with the core purpose ('Returns connection status and URLs'), followed by concise conditional details. No redundant or filler language; 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 zero-parameter, read-only tool with no output schema, the description adequately explains the return behaviors (authenticated:true, pending[], connect_url). It could clarify what 'per-install URLs' means, but overall it is sufficient 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, and the schema coverage is 100% (vacuously). Per the rubric, a baseline of 4 is appropriate. The description does not need to elaborate on parameters since there are none, and it adds no misleading parameter information.

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: 'Returns connection status and URLs.' It distinguishes itself from siblings like 'authenticate' by focusing on status checking rather than initiating authentication, and provides specific outcomes (authenticated:true, empty pending[], connect_url).

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 this tool is for checking connection status, but it does not explicitly state when to use it versus alternatives like 'authenticate'. The conditional behavior (when providers connected vs. missing credentials) gives context, but there is no explicit 'use this when' or 'use authenticate instead' 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 read-only, idempotent, and non-destructive behavior. The description adds meaningful context: prepaid credit consumption per query, no platform credentials required, non-confidential official data, and LGPD accountability. This goes beyond the schema and annotations, though it doesn't mention rate limits or response 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 concise, using three short sentences to convey purpose, payment model, and legal context. There is slight repetition of 'official source' and 'official bodies', but overall it is front-loaded and efficient.

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?

There is no output schema, no parameter descriptions, and no mention of return type or expected response. While it provides high-level purpose and legal/payment context, an agent would be uncertain about what the tool returns and how to map the required inputs to their real-world meaning.

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 3 required string parameters with 0% coverage, and the description never explains login_usuario, login_senha, or numero_instalacao. It mentions credentials generically but doesn't clarify that these are Cemig professional login credentials or that numero_instalacao is the electricity installation number, leaving the agent with no 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 clearly identifies the tool as a Cemig bill download/query service for professionals, using official sources. This distinguishes it from the generic siblings (authenticate, connect, marketplace, etc.), though it could be more explicit by stating the exact action and return type in a verb-driven sentence.

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 implies when to use: to query official Brazilian data without platform credentials, paying with prepaid credits, under LGPD responsibilities. However, it doesn't explicitly name alternatives or exclusions, leaving the use case implied rather than fully specified.

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 substantial behavioral context beyond the annotations. It explains the one-off execution model of invoke, the connect-link behavior for missing credentials, the checkout/top-up link for insufficient wallet funds, the retry workflow, and the workspace-owner/admin requirement for writes. It also discloses installed_in_toolkit vs installed_in_workspace flagging. This goes far beyond what readOnlyHint/openWorldHint/idempotentHint/destructiveHint convey.

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 every sentence conveys necessary operational or selection information. It is well-structured: core flow, key invoke behavior, install-vs-invoke distinction, other actions, permissions, and the prompt library are separated logically. No filler or repetition 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 tool with 23 parameters and no output schema, the description covers a remarkable amount: core flows, auth, payment, permissions, installed-status flags, and prompt-library semantics. The only notable omissions are detailed return-value expectations and the resume action, which is listed in the schema but never mentioned in the description. Still, this is highly complete for its complexity.

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 carries the burden of explaining parameters. It does explain the meaning of many action values (search, describe, invoke, install, list_tools, etc.) and the role of tool_id in selecting a tool. However, it does not cover numerous non-action parameters such as arguments, immediate, tier_slug, conversation, prompt_vars, cancel_reason, or request_details. It provides high-level action semantics but lacks precise parameter-level guidance, leaving gaps for an agent trying to construct a complete request.

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 clear, specific declaration: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then names the concrete capability requests it handles ('find an MCP that does X', 'consulta um CPF') and outlines the search → describe → invoke flow. This strongly distinguishes it from siblings 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?

Usage guidance is explicit and comprehensive. It contrasts invoke vs install with direct instruction: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It also clarifies when to use list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt-library functions, providing both positive and negative selection criteria.

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 a useful detail about including the conversation for reproduction, which goes beyond annotations. However, annotations already disclose idempotency, read-only, and destructive hints. The description remains consistent with these annotations, though it doesn't elaborate on side effects or outcomes. It provides moderate value beyond what annotations already state.

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, directly addresses the purpose and a critical usage detail, and contains no fluff. Every word earns its place, making it highly efficient.

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 feedback tool with 3 flat parameters and no output schema, the description covers the essential context, especially the conversation reproduction detail. The only minor gap is the undefined 'context' parameter, but overall it is adequately complete for the tool's complexity.

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 is the only guide for parameters. It explicitly explains the 'conversation' parameter (calling it an array) and implies the 'message' parameter is the bug/feedback text. However, the 'context' parameter is left undefined, and the description's use of 'array' slightly conflicts with the schema's string type for 'conversation'. It partially compensates for the lack of schema 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 with a specific verb ('Report') and resource ('a bug, missing feature, or send feedback'). It effectively distinguishes itself from sibling tools like 'authenticate' and 'connect' by focusing on bug/feedback submission. The additional instruction to include the conversation array adds clarity about its role in reproduction.

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 explicitly tells when to use the tool ('Report a bug, missing feature, or send feedback') and gives a key usage instruction ('Include the conversation array...'). While it doesn't explicitly name alternatives, the sibling tools are contextually unrelated, making the intended usage clear without needing 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 readOnly, idempotent, and non-destructive behavior. The description adds no further context (e.g., about rate limits or side effects), but the existing annotations sufficiently cover transparency. No contradiction between description and 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, concise sentence that directly conveys the tool's purpose with no unnecessary details. It is well-structured 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?

There is no output schema, but the description implies the tool returns version information, which is enough for a simple read-only operation. It doesn't specify the output format, but for a version check, this is acceptable and not misleading.

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, which matches the description. Since there are no params to explain, the baseline score of 4 applies, and the description correctly omits param details.

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: showing current MCP platform and adapter versions. The verb 'Show' and specific resource 'current MCP platform and adapter versions' precisely define its purpose, distinguishing it 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 does not explicitly state when to use this tool versus alternatives, but it is a straightforward version check with no clear alternative in the sibling set. The intent is implicit, but an explicit note about when to call it (e.g., for diagnostics) would improve clarity.

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 specifying what state is returned (installed MCPs, connection status, accounts, catalog tool counts), which is useful behavioral context 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 conveys all essential information without redundancy or filler. Every word contributes to understanding the tool's 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?

For a zero-parameter, read-only state inspection tool with strong annotations, the description fully covers what the tool returns and when it is relevant. No output schema exists, but the enumerated return contents are sufficient for this simple 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, so the baseline is 4. The description does not need to explain parameter semantics, and no parameter information is missing.

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 identifies the exact resource ('current toolkit state') with enumerated content: installed MCPs, connection status, accounts, and catalog tool counts. This clearly distinguishes it from sibling tools like connect or 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 makes the use case clear: call this tool when you need an overview of the toolkit's current state. It does not explicitly mention alternatives or exclusions, but the context is sufficiently clear given the sibling tools.

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