SABESP: Lista de Instalações

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

The description adds meaningful behavioral context beyond the annotations: it explains the permanent vs session-only distinction and the no-args link-return behavior. Annotations already indicate idempotency and non-destructiveness, and the description does not contradict them. Side effects like token storage are only implied, not fully detailed.

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 and packs important workflow details into two sentences. It is front-loaded with the purpose and includes code-style examples, though the flow is slightly dense and could be broken into clearer steps.

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 the main usage modes, configuration options, and token format. It does not mention error cases or return values, but the simplicity of the tool and the explicit examples make it sufficiently complete.

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 provides only a bare string property with no description and 0% coverage. The description compensates by explaining that the token is a JWT, how to pass it ('{ token: "<jwt>" }'), and that it is optional since calling with no args returns the login link. This adds the necessary 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 explains that this tool handles authentication for MCP.AI by logging in and providing an access token, or accepting a pasted token. It gives a specific workflow and distinguishes the session-only vs permanent configuration paths, though it does not explicitly differentiate from the sibling tool '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 provides concrete usage guidance: add the token to server config for a permanent connection, or call with a token for session-only login, or call with no arguments to receive a login link. This is actionable context, though it does not explicitly state when to prefer this tool over 'connect'.

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 and idempotentHint, and the description adds valuable state-dependent behavior: it explains that 'authenticated:true' and empty 'pending[]' appear when all providers are connected, and that 'connect_url' is returned when credentials are missing. This goes beyond the annotations by clarifying response structure and edge cases.

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 three concise sentences with the main function front-loaded ('Returns connection status and URLs') followed by conditional details. Every word earns its place; no redundancy or 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 no-parameter tool with annotations, the description covers the main output states sufficiently. It could elaborate on intermediate states (e.g., partial provider connections), but given the tool's simplicity and the presence of annotations, it remains complete enough for an agent to use 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 no parameters (0 params), so baseline is 4 per rubric. The description doesn't need to compensate, and schema coverage is vacuous. The tool's behavior is fully described without needing parameter explanations.

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', which is a specific verb and resource. It also distinguishes itself from siblings like 'authenticate' and 'toolkit_info' by detailing different output conditions (all providers vs. missing credentials).

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 context is implied through the description—e.g., if you need connection status, use this tool—but there is no explicit 'when to use' guidance or mention of alternatives. The behavior described makes the use case clear, but it lacks exclusions or comparisons to siblings.

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?

Beyond the annotations (read-only, idempotent), the description reveals that the tool requires payment via prepaid credits, does not use platform credentials, and accesses non-confidential public data. These additional behavioral details enhance transparency beyond the basic 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 paragraph but is verbose with repetitive legal phrasing (e.g., 'consulta em fonte oficial' and 'consulta informação de fontes e órgãos oficiais'). It front-loads the core purpose but includes redundant disclaimers, making it less concise than necessary.

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 nature of the tool (listing installations), the description lacks essential context such as input parameter requirements, expected output structure, or error handling. The legal disclaimers are present but do not compensate for missing functional details, leaving the tool's behavior incomplete.

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 provides no explanation for the parameters (cnpj, login_cpf, login_senha). Since the schema has no descriptions either (0% coverage), the description fails to compensate, leaving users to guess the meaning and required format of each 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 states 'Lista de Instalações' (List of Installations) and mentions consulting an official source, which clearly indicates the tool's purpose. However, it does not specify the type of installations (e.g., water service) beyond the tool name, leaving some 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 does not provide guidance on when to use this tool versus alternatives. Sibling tools like authenticate or marketplace serve different purposes, but no explicit usage scenarios or comparisons are given. The payment and legal disclaimers are mentioned but not tied to specific use cases.

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?

Goes well beyond annotations by disclosing key behaviors: invoke runs tools even when not installed, returns connect/checkout links for auth or payment, and writes require workspace owner/admin. It also notes that invoke avoids bloating the tool list and that search/describe flag installation status, adding useful side-effect 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 dense paragraph of roughly 350 words. It is front-loaded with the main purpose and core flow, and every sentence adds information, but the lack of bullet points or section breaks makes it harder to scan. Length is justified by the tool's complexity, but structure could be improved.

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?

Covers major flows, auth/payment edge cases, permission requirements, and the prompt library. With no output schema, it even hints at return behaviors (e.g., shareable link, connect link). However, it omits details on the response format of search/list_tools and some sub-actions like resume, leaving minor 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?

With 0% schema description coverage, the description compensates by explaining the central 'action' parameter and the roles of tool_id, mcp_id, and prompt-related fields. However, 23 parameters means many (e.g., limit, immediate, tier_slug) are not individually described, though the high-level flow covers their purpose indirectly.

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 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly stating the tool's role. It differentiates itself from siblings by being the central hub for marketplace operations and explicitly defines the core search → describe → invoke flow.

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 explicit guidance: use invoke for one-off/occasional use, install only for permanent additions, request_mcp when nothing fits, and lists other actions like list_tools and subscribe/cancel. It also explains the retry flow when credentials or payment are needed, making when-to-use decisions clear.

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 this is a non-read-only, non-destructive, idempotent operation. The description adds the reproduction instruction but does not disclose other behavioral traits such as how the report is processed, whether a confirmation is returned, or potential side effects. It does not contradict 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 purpose front-loaded. Every word earns its place, and the parameter instruction is concise and actionable. No 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 tool is simple, with no output schema and no nested objects. The description covers the core purpose, one key parameter instruction, and aligns with annotations. It lacks detail on expected return or side effects, but given the simplicity and annotation coverage, it is adequate for an agent to invoke 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?

Schema coverage is 0%, so the description must compensate. It explains the 'conversation' parameter's purpose ('recent messages for reproduction'), adding meaningful context beyond the schema. However, 'message' and 'context' are left to their names, and their exact semantics are not elaborated, so compensation is partial.

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: 'Report a bug, missing feature, or send feedback.' The verb 'Report' and resource scope are specific, and the inclusion of 'missing feature' and 'feedback' broadens the scope appropriately. It is clearly distinct from sibling tools like authenticate 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 implies usage for reporting bugs/feedback, which is distinct from sibling tool functions. It gives practical guidance on using the 'conversation' parameter for reproduction, but does not explicitly state when not to use the tool or mention alternatives. Since siblings are unrelated, the lack of exclusions is not a major gap.

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 is read-only, idempotent, and non-destructive. The description consistently says 'Show' but does not disclose further behavioral details like return format or network access. Since annotations cover the safety profile, the minimal description is acceptable but not enriching beyond the structured 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?

A single, direct sentence that communicates exactly what the tool does without any extra words. Perfectly concise for a version-inspection 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 zero-parameter tool with no output schema, the description covers everything needed. It fully addresses the purpose and leaves no ambiguity about behavior, making it complete within its scope.

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, this dimension meets the baseline of 4. The description adds no parameter-specific details because none exist, so no compensation is needed.

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 ('MCP platform and adapter versions'), making it clear what is displayed. It naturally differentiates from sibling tools like authenticate or connect, which have entirely 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 that it is used to check version information, but it does not explicitly state when to use this tool or mention any alternatives. For a trivial version tool, the usage is clear enough, though it lacks the explicit guidance seen in stronger examples.

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 no safety ambiguity exists. The description adds value beyond annotations by specifying what the returned state includes (installed MCPs, connection status, accounts, catalog tool counts), which is useful behavioral context for a retrieval tool.

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 immediately states the tool's purpose and lists the key data points. Every word earns its place; there is no filler or redundant phrasing.

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 info tool with no output schema, the description fully covers what the agent should expect: installed MCPs, connection statuses, connected accounts, and catalog tool counts. No additional behavior or return-format details are necessary for correct invocation.

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 per the rubric. The description needs to explain no parameter semantics, and it correctly focuses on the return content instead.

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 a clear resource ('current toolkit state'), then enumerates the exact content: installed MCPs, connection status, accounts, and catalog tool counts. This distinguishes it from siblings like show_version and report_bug, which cover different aspects.

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 clear that this tool is appropriate when the agent needs an overview of the toolkit's MCP connectivity and account bindings. It does not explicitly name alternatives or exclusions, but the context is obvious given the zero-parameter, read-only nature and sibling tools like connect/authenticate that fulfill different roles.

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