SABESP: Download de Conta

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

Beyond the annotations, it discloses the browser login flow, the permanent/non-expiring nature of the config-header option, the session-only nature of the token paste, and the no-args link behavior. This is rich behavioral context and 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?

The description is compact and information-dense, front-loaded with the tool's purpose and audience. It is slightly run-on, but every clause contributes useful guidance.

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 tool with one optional parameter and no output schema, the description covers permanent and session modes, invocation patterns, and the no-arg link behavior. It does not describe response/error details, but those are not essential here.

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 only declares token as an optional string, so the description compensates by explaining that token is a pasted JWT/access token and by showing call shapes with and without it. It could mention invalid-token behavior, but the meaning of the only parameter is clear.

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 names the authentication action for MCP.AI IDE agents and explains the browser login/token flow. It does not explicitly contrast with the 'connect' sibling tool, so sibling differentiation is only implicit.

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 distinguishes usage modes: a permanent config-header approach versus a session-only token paste, and states that no args returns the login link. This gives the agent concrete when-to-use guidance and alternatives within the tool.

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 behavioral context beyond the annotations by explaining the two states (connected vs. missing credentials) and the corresponding return fields. This includes what happens when credentials are missing, which is useful. The annotations already declare readOnlyHint and idempotentHint, so the description does not need to repeat safety. No contradictions.

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, with three sentences each providing value: the main purpose and two conditional outcomes. No redundant or filler content. It is front-loaded with the main 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 simple tool with no parameters and no output schema, the description covers the main behavior and both possible outcomes. It explains the authenticated flag and the URLs returned. Some details like the structure of pending[] are not explained, but overall it is sufficiently complete for an agent to understand what to expect.

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 no parameters, so the description cannot add parameter semantics. The baseline for zero params is 4, and the description is not penalized for omitting 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 clearly states the tool returns connection status and URLs, using the specific verb 'returns' and resource 'connection status'. The mention of 'authenticated:true' and 'connect_url' clarifies the output states. It distinguishes from the sibling 'authenticate' by focusing on status/URLs rather than performing authentication, though not explicitly.

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 checking connection status, particularly when credentials are missing or after setup. It describes conditional behavior but does not explicitly say when to use this over alternatives like 'authenticate'. There is no mention of when not to use it.

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 states it uses official sources, is hosted by the platform, and emphasizes data privacy and LGPD compliance. It also notes that no platform credentials are required. However, it does not describe the exact behavior of the download (e.g., whether it returns a file, what format) or any potential side effects beyond payment.

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 somewhat verbose and repetitive, with multiple sentences that could be condensed. It repeats the idea of official source and data privacy, 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?

The description lacks essential details such as the meaning of parameters, expected output, and how the tool fits into the overall workflow. It does not mention the return format or any constraints, leaving the agent with insufficient information to invoke it 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 description provides no information about the parameters (cnpj, ano_mes, login_cpf, login_senha, fornecimento) or how they should be used. Since the schema has no descriptions, the agent has to guess what each field means.

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 is for downloading an account from SABESP via an official source, which is a specific action. However, it could be more precise about the exact type of account (e.g., bill, statement) but overall it conveys the primary function.

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 compared to other tools. It mentions that it requires login credentials and payment, but does not explain the scenario for using this tool over alternatives like 'authenticate' or '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?

The description adds substantial behavioral context beyond the annotations: invoke works even when an MCP is not installed, runs one-off without bloating the toolkit, and requires owner/admin for writes. It also discloses credential-link and payment-link behavior, installation flags, and prompt-link visibility. The annotations (readOnlyHint=false, openWorldHint=true) are consistent with this description.

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 front-loaded with the core flow, then covers write actions, prompt library, and permission context. Though it is a long single paragraph, most sentences add necessary information for a large multi-action tool. Formatting into sections would improve scannability, but the content is not wasteful.

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 high complexity, 23 optional parameters, and no output schema, the description covers the main workflow, auth/permission requirements, billing edge cases, and the prompt-library subdomain. It does not describe return shapes or enumerate every action (e.g., resume is not mentioned), but it provides enough context for an agent to operate effectively.

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 23 parameters and 0% schema description coverage, the description carries a heavy burden and largely delivers: it explains action=search, describe returning tool_id + params + pricing + auth, invoke running a tool, install vs invoke semantics, and prompt-related actions. However, several parameters remain under-explained, such as immediate, tier_slug, conversation, prompt_targets, cancel_reason, and the JSON string formats for arguments/prompt_vars.

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/execution layer, distinguishing it from sibling tools like authenticate, connect, and report_bug. It provides concrete capabilities (search, describe, invoke, install, prompts) and explicitly frames the core flow from discovering MCPs to running them.

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 strong when-to-use guidance: use invoke for one-off runs, install only to make an MCP permanent, list_tools for currently callable tools, request_mcp when nothing fits, and report_bug for feedback. It also explains conditional flows (connect link for credentials, checkout/top-up for paid tools) and permission requirements for writes.

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 communicate idempotency, non-destructiveness, and non-read-only behavior. The description adds the purpose of the conversation parameter ('for reproduction') but does not disclose side effects, response behavior, or prerequisites. It is consistent with annotations and provides a moderate amount of extra 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, compact sentence that front-loads the tool's purpose before giving the key usage instruction. There is no filler, redundancy, or schema repetition.

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 tool with three plain parameters and no output schema, the description is mostly sufficient: it identifies the purpose, the key required input, and why the conversation data matters. Minor gaps are the unexplained context parameter and the precise serialization of the conversation value.

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, and it partially does: it explains the conversation parameter's role for reproduction. The required message parameter is reasonably implied by 'Report a bug...', but the context parameter is never explained, and saying 'conversation array' is slightly ambiguous given the schema defines it as a string (default '[]').

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 specific verb 'Report' and names concrete resource types: a bug, missing feature, or feedback. It also adds the reproduction detail about including the conversation array, which makes the tool's scope clear and distinct from unrelated 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?

The description implies when to use the tool—when reporting a bug, missing feature, or feedback—and gives a concrete instruction to include recent messages for reproduction. However, it does not provide explicit when-not-to-use guidance or name alternatives, leaving usage largely implied.

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 is consistent with the annotations (readOnly, idempotent, non-destructive). The verb 'Show' correctly indicates a read-only operation, and no contradictions exist. Annotations already cover these aspects, so the description adds minimal but accurate 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 conveys the essential purpose without unnecessary detail. It is well-structured and directly to the point.

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 is complete for its simplicity: it specifies what is shown (MCP platform and adapter versions) and implies no return format is needed. With no output schema and no parameters, the description fully covers the tool's function.

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 no parameters, and the schema coverage is trivially 100%. According to the rubric, zero parameters warrants a baseline of 4. The description adds no extra parameter information, which is appropriate since none exist.

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: showing the current MCP platform and adapter versions. It uses a specific verb ('Show') and identifies the resource (versions), 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 implies usage (when you need version information) but does not explicitly contrast with alternatives. Since it's a simple query tool with no side effects, the context is sufficient, though it could explicitly mention 'use this when checking version compatibility or environment details.'

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=false, so the safety profile is covered. The description adds value by specifying exactly what information is returned (installed MCPs, connection status, accounts, catalog tools), which goes beyond the annotations and clarifies the tool's 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 a single, well-structured sentence that front-loads the main purpose ('Returns the current toolkit state') followed by concise enumeration of the specific data it provides. Every phrase adds information and there is no redundancy or filler.

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 inspection tool with no output schema, the description fully conveys what the tool does and what it returns. It includes all necessary details to understand the tool's behavior without requiring additional context.

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 according to the rule the baseline is 4. There is nothing to describe, and the schema already reflects the absence of parameters with an empty properties object.

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 names the exact resource ('current toolkit state'), then enumerates the components: installed MCPs, connection status, accounts, and catalog tool counts. This clearly distinguishes it from sibling tools like authenticate or connect, which are action-oriented.

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 explicit when-to-use guidance is provided, but the description's nature as a state-inspection tool makes the use case obvious. It does not mention alternatives or exclusions, so it lacks the explicit guidance needed for a 5, yet the purpose alone conveys the appropriate context for a 3.

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