Prefeitura SP Araçariguama: NFS-e (Nota Fiscal Eletrônica de Serviços)

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

Annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true) are supplemented by the description, which clarifies the authentication flow and side effects like creating a permanent config header vs. session-only token. The description adds transparency about the token's lifespan (non-expiring vs. session-only) and the fact that calling with no args returns a login link, which is beyond what the annotations reveal.

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, somewhat run-on block of text with colons and 'Best:' and 'Or' to separate ideas, which could be better structured with line breaks or bullets for scanability. Every piece of information is relevant, but the flow is a bit tangled, making it less concise than it could be.

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, the description covers the main usage patterns (config header, token paste, no-arg) and enough context to invoke it correctly. It does not describe the response format, but the absence of an output schema and the low complexity keep this from being a critical gap.

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 0% schema description coverage, the description explicitly explains the `token` parameter as a JWT to paste, and clarifies that calling with no arguments retrieves a login link. This directly adds meaning beyond the bare schema (which only states 'string'), effectively covering the parameter's semantics in prose.

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: to authenticate MCP.AI for IDE agents by logging in, copying an access token, and making it available via a config header or session token. It includes a specific flow (browser login, copy token) and differentiates between permanent (config header) and session-only (paste token) usage, which distinguishes it from sibling tools like 'connect' and 'report_bug'.

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 clearly explains when to use the tool (authentication) and provides instructions for the recommended permanent config method versus a session-only approach, including when to call with a token and when to call with no arguments. However, it does not explicitly contrast with siblings like 'connect' or mention alternative tools to consider, leaving a small gap in 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 indicate read-only and idempotent. The description adds context about the return values and conditions (authenticated:true vs connect_url), which is useful transparency 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?

Two concise sentences, no fluff. Clearly structured with conditions and expected returns.

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?

Without an output schema, the description explains the expected return structure and two possible states. It adequately covers the functionality, though it doesn't mention error scenarios.

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?

No parameters, so schema coverage is complete. Description doesn't need to explain parameters. Baseline for zero params is 4, and description doesn't need to add more.

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, and explains two distinct scenarios. It's a specific verb+resource (returns status) and distinguishes from sibling 'authenticate' which is about authentication.

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 (checking connectivity) but does not explicitly state when to use this tool versus alternatives like 'authenticate'. No explicit guidance for 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?

Beyond the annotations, it discloses major behavioral traits: invoke runs tools even when the MCP is not installed, one-off invocations do not bloat the toolkit, writes require workspace owner/admin, and credential or payment gaps trigger connect/checkout links. It also describes the prompt library's behavior, including shareable unauthenticated links, adding substantial context not present in 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 long but justified by the tool's 14-action dispatcher and 23 parameters. It front-loads the core purpose and flow, uses arrow notation for the main path, and separates the prompt library subsection. Some density and lack of formatting make it moderately heavy to parse, but every major behavior 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 highly complex tool with no output schema, the description covers the essential discovery, invocation, installation, billing, permission, and prompt-library behaviors. It explains return behaviors such as connect links, checkout links, full prompt text, and shareable slugs, but it does not describe response shapes for actions like search, list_tools, report_bug, or request_mcp, leaving some gaps for the agent.

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 parameter-semantics burden and does so well for the core workflow: it explains action values, mcp_id, tool_id, arguments, prompt_slug, prompt_body, and prompt_vars via the search/describe/invoke and prompt-library flows. However, some parameters remain unexplained, such as immediate, tier_slug, conversation, prompt_targets, and cancel_reason, so it is not fully exhaustive.

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 mcp.ai marketplace catalog and execution layer, with specific verbs like 'discovers MCPs by intent', 'returns one MCP's full profile', and 'invoke RUNS that tool.' It also distinguishes its scope from sibling tools by explaining that it spans catalog search, execution, installation, billing, and prompt-library operations.

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 explicit usage direction: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It also provides the core flow (search → describe → invoke) and notes credential/payment link behaviors that tell the agent how to proceed on connect/checkout responses.

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 mark the operation as readOnly, idempotent, and non-destructive. The description adds non-redundant transparency about payment, lack of platform credentials, the non-confidential public nature of the data, and LGPD controller responsibility. It does not describe failure modes or return format, but the annotation layer already covers the safety profile.

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 front-loaded with the core purpose and then gives compact operational and legal context. It is a few sentences long, but each clause contributes non-obvious information about credentials, pricing, data sensitivity, and LGPD obligations.

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 parameterized query, the description covers purpose, access, cost, and data confidentiality well. However, with no output schema, it does not describe the returned data or common input validation requirements, leaving a notable gap for an agent deciding whether the tool's result satisfies a request.

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 of the three required parameters (cnpj_prestador, numero_nota, codigo_verificacao), their formats, or how they relate. With 0% schema description coverage, the description was expected to compensate, but it leaves the parameter semantics entirely to the schema property names.

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 consults NFS-e information from the official Prefeitura SP Araçariguama source. It uses a specific action (consulta) and resource (NFS-e), and it is easily differentiated from the generic sibling tools like connect, marketplace, and report_bug.

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 clear operational context: the tool is an official-source lookup, needs no platform credentials, and is billed per query with prepaid credit. It does not explicitly name alternatives or exclusions, but the context makes the intended use case clear enough.

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, destructive, and idempotent hints. The description adds useful behavioral context by explaining that the conversation array should contain recent messages to help reproduce the issue. It does not go into storage or external delivery, but the safety-relevant traits are already handled by 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 short sentences communicate the tool's purpose, scope, and key reproduction guidance with no filler or repetition. The structure is front-loaded and easy for an agent 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 relatively simple: one required string parameter, no output schema, and descriptive annotations. The description adequately covers what to provide and why, though it just mention what happens after submission or how the response is formatted. Given the low complexity, this is complete enough.

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 for parameter docs. It adds meaningful semantics for 'conversation' (recent messages for reproduction) and indirectly clarifies 'message' as the content being reported. However, 'context' remains undefined, and the description calls conversation an array while the schema types it as a string, leaving format ambiguity.

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 ('Report') and explicitly names the targets: a bug, missing feature, or feedback. This clearly distinguishes it from sibling tools such as authenticate, connect, marketplace, and 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 gives clear usage context: use this tool to report bugs, missing features, or send feedback, and include recent conversation messages for reproduction. It does not explicitly state alternative tools or exclusions, but siblings are unrelated enough that this is not a significant 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the scope of 'platform and adapter versions' but does not disclose any further behavioral traits such as output format, latency, or whether network calls occur.

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 that directly and fully conveys the tool's purpose. There is no redundant wording, filler, or repetition of the tool name.

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, idempotent version-inspection tool with rich annotations, the description is sufficient. No output schema exists, but the description's claim to show versions is clear enough for an agent to select and invoke 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 description coverage is effectively complete since there are no properties to document. The description does not need to explain parameter semantics, so the baseline of 4 applies.

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') with a clear resource ('current MCP platform and adapter versions'). It is unambiguous and sufficiently distinct from sibling tools like 'toolkit_info' or 'connect', as it focuses specifically on version information.

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 no guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. For a zero-parameter version tool this is somewhat less critical, but explicit usage context is still absent.

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 declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, which already inform the agent that this is a safe, repeatable read operation. The description adds value by specifying exactly what the returned state includes (installed MCPs, connection status, accounts, catalog tool count). This exceeds the minimum transparency and effectively communicates the output shape.

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, complete sentence that front-loads the key information ('Returns the current toolkit state') and then lists the details in a clean, readable manner. There is no fluff or repetition, making it exemplary in conciseness and structure.

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?

With zero parameters, no output schema, and a straightforward read-only purpose, this description covers everything needed: what the tool returns and the components of that return. There are no missing prerequisites or side-effects to state, as the annotations already communicate the safe, non-destructive nature. The description entirely fulfills its role.

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 schema provides 100% coverage by having no properties. The description appropriately focuses on the return value rather than parameters. Per the guideline, zero parameters receive a baseline of 4, and the description does not need to add 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 explicitly states the function: 'Returns the current toolkit state' and then enumerates the specific information returned (installed MCPs, connection status, accounts, catalog tools count). This leaves no ambiguity about what the tool does, and it is distinct 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 is self-contained for a zero-parameter read-only tool)Skip the generic usage note. It clearly indicates the tool's purpose without requiring additional guidance. While it doesn't explicitly say 'use this to check status before connecting,' the intuitive semantics make the call natural. A higher score would require an explicit alternative or prerequisite mention, but none are needed here.

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