Cemig: Obter Instalações

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

The description discloses key behaviors such as returning a login link when called with no arguments, accepting a JWT for session login, and differentiating permanent vs session credentials. This adds context beyond the annotations (idempotentHint, readOnlyHint) about side effects and persistence. It could mention rate limits or errors, but for an auth flow it is fairly transparent.

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 functional but somewhat run-on and mixes instructions for the agent and user. It could be broken into clearer bullet points or separated by flow. Still, it is relatively short and avoids 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 an authentication tool, the description covers the essential contexts: how to get a login link, how to pass a token, and the distinction between permanent and session logins. It also suggests a security-best-practice (config header). No output schema exists, so the missing return-value documentation is acceptable. Slight gap: no mention of what happens upon successful authentication (e.g., confirmation or errors).

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?

Although the schema has zero description coverage, the tool description explicitly explains the 'token' parameter: it is a JWT to be passed after the user pastes it. It also clarifies that omitting the parameter retrieves a login link. This compensates well for the schema's lack of detail.

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 handles authentication by providing a login link or accepting a token. It distinguishes between permanent (config header) and session (token) authentication, which clarifies its purpose among siblings like 'connect' and 'marketplace'. However, the phrasing is somewhat cluttered and could be more direct.

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 explains when to use the tool (with no args for a link, or with a token for session login) and even suggests a best practice (config header). However, it does not explicitly compare itself to alternatives or state when not to use it, leaving some ambiguity about its relationship to 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 cover read-only, idempotent, and non-destructive behavior. The description adds value by explaining conditional response behavior: authenticated:true when connected and connect_url/per-install URLs when credentials are missing. 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?

Two sentences with the primary behavior front-loaded and the conditionals placed naturally. Every sentence earns its place; there is 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 tool with no output schema, the description sufficiently explains the meaningful cases: fully connected state and missing-credentials state. The annotations additionally clarify safety, making the tool fully interpretable.

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 schema already fully covers invocation needs. The description does not need to explain parameters, and no ambiguity exists.

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 verb ('Returns') and explicitly names the resource: connection status and URLs. This clearly distinguishes it from the sibling 'authenticate' tool, which presumably establishes the connection rather than reporting on it.

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 conditionals ('When all providers are connected... When credentials are missing...') imply the tool is for checking connection state and retrieving relevant URLs, but it does not explicitly tell the agent when to choose this over 'authenticate' or when not to use it. Usage is implied rather than prescribed.

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 and destructiveHint=false, so the safety profile is known. The description adds useful context: it's hosted by the platform, no platform credentials needed, paid per query, and data is non-confidential. However, it lacks details on what the response contains or any side effects (though it's read-only).

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 of moderate length, providing essential information about the tool's nature, cost, and privacy. It is reasonably concise and does not waste words, though the structure could be improved with bullet points for readability.

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 (4 parameters, multiple possible identifiers, paid service), the description is incomplete. It does not explain how the parameters interrelate (e.g., cpf vs cnpj), what the output will look like, or any prerequisites. The annotations and lack of output schema increase the burden on the description, which it does not fully meet.

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 should compensate. It describes the purpose but does not explain the role of each parameter (cpf, cnpj, email, senha). It mentions 'senha' is required but not what it is for. The description gives no hints on which parameter to use for which scenario, making parameter selection 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 that the tool retrieves installations information from Cemig, an official source. It distinguishes itself from sibling tools like 'authenticate' or 'connect' by specifying a specific data lookup function, though it could be more specific about the exact resource ('instalações').

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 indicates this is for querying official Brazilian data, and mentions the paying model and LGPD compliance. However, it does not explicitly state when to use this tool over alternatives, nor does it mention any exclusions or alternative tools for different queries. The context is clear but not exhaustive.

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 well beyond the sparse annotations, disclosing key behaviors: invoke runs tools one-off even when not installed, does not bloat the tool list, returns connect/checkout links if credentials or payment are needed, and requires owner/admin for write actions. It also clarifies the distinction between permanent install and one-off invoke, and mentions search/describe flags for installed status. This is rich, honest 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 dense and comprehensive, with no filler, but it is quite long. It is front-loaded with the core purpose and then systematically covers actions, invoke semantics, install vs. invoke, permissions, and prompt library. While each sentence adds value, the wall-of-text format could be more scannable; still, it earns its 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?

For a tool with 23 parameters, no output schema, and open-world side effects, the description covers a huge amount: core flow, auth/payment behavior, install/invoke distinction, permissions, support actions (report_bug, request_mcp), and the prompt library. It even specifies return links for credential/payment cases. It is not exhaustive—e.g., it does not specify output formats for search results—but it is remarkably complete for a complex 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?

With 0% schema description coverage, the description must compensate. It does explain the central parameters through context: action (search/describe/invoke/install/etc.), mcp_id, tool_id, arguments, prompt_slug, prompt_vars, and prompt_tool are referenced in the flow. However, several parameters like limit, immediate, conversation, report_context, and request_details are not explicitly defined, though some can be inferred from associated actions. Residually, not all 23 parameters receive direct 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 clearly identifies the tool as 'the official mcp.ai marketplace' with a specific resource and scope. It distinguishes itself from siblings by explaining its role as the catalog and execution layer for MCPs/tools, with explicit capabilities like searching, describing, installing, and invoking. The verb+resource structure is 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?

The description provides explicit when-to-use guidance: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT in the active toolkit', and outlines a core flow (action=search → describe → invoke). It also notes permissions ('Writes require workspace owner/admin') and alternatives like list_tools for currently callable tools. This gives clear decision rules for the agent.

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 provide readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description doesn't contradict these, but it doesn't add behavioral context beyond the annotations. It says to include the conversation array for reproduction, which is an additional non-annotation detail, but is scant.

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, appropriately concise, and places the key action first. It has no filler, though it sacrifices detail for brevity.

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 no output schema, 3 parameters with 0% coverage, and sparse annotations, the description is insufficient. It doesn't explain required fields, parameter syntax, or expected behavior (e.g., whether feedback is anonymous, response format). The tool is simple but still lacks essential guidance.

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%, and the description only mentions 'conversation' array, leaving 'context' and 'message' unexplained. 'message' is required but its role is obvious from the name; 'context' is entirely undocumented. The description fails to compensate for the schema gap.

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 states it reports bugs, missing features, or sends feedback, which is clear enough, but it doesn't specify the exact resource or differentiate from sibling tools (though none are similar). It's not a tautology but lacks specificity about what constitutes a bug report.

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 on when to use this tool versus alternatives; there are no similar sibling tools, but it doesn't say when not to use it or provide any exclusions. The description implies it's for reporting issues but lacks explicit 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect behavior. The description adds no additional behavioral context beyond stating what it shows, but it does not contradict annotations. With strong annotations, this is acceptable, though minimal extra context 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 with zero waste. It immediately communicates the action and object, making it highly efficient 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?

The tool is simple, has no parameters, and annotations fully cover safety semantics. The description explains what it does without needing to detail output format (though no output schema exists, the output is self-evident). It is complete for its simplicity, though it could optionally mention that it returns version strings.

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 trivially 100%. The description adds meaning by specifying the exact content shown (platform and adapter versions), which is not present in the schema. Baseline for 0 params is 4, and the description meets that standard.

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 resource ('current MCP platform and adapter versions'), clearly distinguishing it from siblings like authenticate or connect. It precisely states what the tool does without 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?

The description implies the tool is for retrieving version information but provides no explicit guidance on when to use it versus alternatives. No exclusions are mentioned, and the context is clear from the verb and resource, but it lacks explicit usage direction.

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 safety profile is clear. The description adds value by specifying exactly what state is surfaced (MCPs, connections, accounts, tool counts), giving the agent a concrete picture of the informational scope 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, well-structured sentence that front-loads the main action and then lists each returned component. Every phrase contributes meaningful information, 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, read-only informational tool, the description fully captures what the agent needs to know: the tool returns an overview of toolkit state with specific granularity. No output schema exists, but the description provides sufficient detail about the returned categories without needing exhaustive format documentation.

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. There is no parameter nuance to add, and the description focuses appropriately on the return content instead of inventing unnecessary parameter 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 names a specific verb ('Returns') and a concrete resource ('current toolkit state'), then details the exact data categories: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly differentiates it from siblings like report_bug or show_version, which serve 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 this tool is for inspecting toolkit state, but it does not explicitly state when to use it versus alternatives or when not to use it. There are no exclusions or conditionals, so usage guidance is only implicit.

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