Prefeitura SP Osasco: Certidão de Tributos de Imóveis

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

Annotations already declare the tool is idempotent and non-destructive. The description adds valuable context: it creates a browser-based login flow, returns a link with no args, accepts a pasted JWT, and distinguishes permanent vs session-scoped authentication. It does not fully describe error handling or the exact response shape, but the additional behavioral detail is meaningful.

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 and front-loaded with context. It is information-dense, but the second sentence is a single run-on with and-d or-splitting three possibilities; it could be slightly clearer with bullet points, but overall it is efficient and without 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?

Given the tool has one optional parameter and no output schema, the description sufficiently covers the authentication flow, both token modes, and the recommended permanent configuration. It does not mention failure scenarios (e.g., invalid token), but the essential information for an agent to use the tool is present.

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 defines 'token' as a string with no description, but the tool explains that the token is a JWT pasted by the user, that it is optional (since no args produces a link), and that it provides session-only access. This compensates well for the 0% schema description coverage.

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: authenticate a user for MCP.AI server by logging in via browser and retrieving an access token. It also differentiates between permanent config-based access and session-only token-based access, making it distinct from siblings like 'connect' or 'marketplace'.

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 instructions on when to use each mode: no args to receive the login link, with a pasted token for session-only login, and recommends the config-header approach for permanent access. This clearly guides the agent on the appropriate invocation 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, idempotentHint, and destructiveHint, covering the safety profile. The description adds behavioral context by detailing conditional output structures (authenticated:true vs connect_url), going beyond annotation scope. No contradiction exists.

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?

Three sentences that front-load the tool's purpose and detail conditional outcomes without redundancy. Every sentence contributes to understanding the tool's behavior.

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 simplicity (no parameters, no output schema), the description adequately covers the response format in different states. It might benefit from specifying what pending[] contains or the nature of URLs, but it is sufficient for an agent to understand expected responses.

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 schema coverage is trivially 100% and there is no parameter ambiguity. The description focuses on output rather than inputs, which is appropriate given the lack of parameters, meeting the baseline for 0-param tools.

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, with specific conditional outputs based on provider connectivity. It distinguishes itself from siblings like authenticate by focusing on status retrieval rather than 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 explains behavior in different credential states but lacks explicit guidance on when to use this tool versus alternatives. It implies use for checking connectivity but does not mention exclusions or refer to sibling tools, leaving the agent to infer appropriate usage.

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 are minimal (readOnlyHint=false, openWorldHint=true, etc.), so the description carries the full burden. It discloses key behaviors: invoke runs tools even when not installed, returns connect/checkout links for auth/payment, and the one-off install behind invoke. Also clarifies write permissions. No contradictions 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 long but information-dense. It starts with the core purpose and immediately describes the flow, then covers key behaviors and permissions. Every sentence adds value, though some repetition (e.g., 'KEY: invoke works even when the MCP is NOT installed') could be tightened. The structure is logical: core flow, invoke specifics, install distinction, list_tools, subscription, and prompt library.

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 multi-action tool with 23 parameters and no output schema, the description is remarkably complete. It explains the primary user journeys, edge cases (auth/payment), permission model, and even the prompt library subsystem. No output schema exists, but the description describes expected outcomes (e.g., invoke returns links, describe returns profile). This is sufficient for an agent to use the tool 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?

Schema coverage is 0%, but the description adds meaning to the critical parameters, especially 'action' by explaining each action's role (search, describe, invoke, install, etc.). It also implies the meaning of mcp_id, tool_id, and arguments through the flow description. However, it does not explain parameters like limit, query, cancel_reason, or prompt_* fields in detail, leaving some gaps.

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: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It distinguishes from siblings by explicitly naming list_tools as a separate tool and describing the unique invoke capability. The core flow (search→describe→invoke) is clearly articulated.

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?

Extensive usage guidance: explains when to use invoke vs install ('prefer invoke for a single/occasional use'), states permission requirements ('Writes require workspace owner/admin'), and covers edge cases like credential/login and payment links with retry instructions. Also mentions how search/describe flags distinguish installed states.

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?

Adds meaningful behavioral details beyond annotations: payment per query via prepaid credit, no platform credentials required, and LGPD compliance/controller responsibility. These are not captured by readOnlyHint, idempotentHint, or destructiveHint and are valuable for the agent to understand cost and legal implications.

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 front-loaded with the purpose, then adds relevant business context. It is a single, coherent paragraph with no redundant filler, though it could be slightly restructured to separate operational details from 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?

Given five required parameters and no output schema, the description fails to mention return values or parameter meanings. It only states the tool is a query for official property tax certificates, leaving the agent uncertain about what data it receives and how to fill the required fields, making it incomplete for effective selection and 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?

Schema description coverage is 0%, yet the description does not explain any parameter (cdc, finalidade, cpf_solicitante, telefone_solicitante, email_solicitante). With five required parameters and no semantic guidance, the agent cannot infer what each field expects, making this dimension critically weak.

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?

Clear and specific: it states the tool queries property tax certificates (Certidão de Tributos de Imóveis) from the Prefeitura SP Osasco, using the verb 'consultar' (to query) and a specific resource. It distinguishes itself from the generic platform siblings by naming the municipality and certificate type.

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?

Implies usage for querying Osasco property tax certificates but does not explicitly state when to use it over alternatives or when not to use it. It provides context about payment and official source, but no explicit exclusion or comparison, though no similar tool exists among 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?

Annotations cover readOnlyHint, destructiveHint, and idempotentHint, so the basic behavioral safety is already declared. The description adds useful context that the conversation array is needed for reproduction, but it does not disclose potential side effects such as external data transmission, which would be relevant for a 'send feedback' action.

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, front-loaded with the tool's purpose followed by a practical usage hint. There is no redundant wording or unnecessary detail.

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 three-parameter tool with no output schema and unrelated siblings, the description provides enough guidance to invoke it correctly: it names the report types, suggests including the conversation array for reproduction, and the schema clarifies required fields. The only minor gap is the undocumented context parameter, which has a default value and is likely optional.

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 must carry parameter meaning. It partially does: 'conversation array with recent messages' clearly maps to the conversation parameter, and the first sentence implies message contains the bug/feature/feedback text. The context parameter, however, is not explained or even mentioned.

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') plus the target resources ('a bug, missing feature, or send feedback'), making the tool's purpose unmistakable. This clearly distinguishes it from unrelated sibling tools like 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 clearly states when to use the tool: for reporting bugs, missing features, or feedback. It also gives an actionable instruction to include the conversation array with recent messages for reproduction, though it does not explicitly discuss when not to use it or name 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?

No annotations are provided, so the description carries full burden. It only states the action without mentioning output format, potential absence of versions, or any side effects. It lacks details on what the response includes.

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?

Single sentence, overly concise but not under-specified: it fully communicates the tool's purpose without waste.

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 parameters, simple purpose, but lacks output schema and no behavioral details; description is adequate but incomplete regarding return format and limitations.

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 100% (empty object), so the description adds no param info. Baseline 4 applies for no parameters.

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 the tool shows current MCP platform and adapter versions, which is a specific verb and resource. It distinguishes from siblings like toolkit_info (which likely provides broader toolkit info) but does not explicitly differentiate.

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 general usage for checking versions, but no explicit guidance on when to use versus alternatives. It doesn't mention prerequisites or scenarios where version info is relevant.

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, establishing a safe read-only behavior. The description adds context about the returned content (installed MCPs, connection status, accounts, catalog counts), which is useful but does not disclose additional behavioral traits such as potential latency or authentication requirements.

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 with the main action front-loaded and a colon-delimited list of return contents. Every phrase adds information without 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 status tool, the description specifies all the relevant output categories (installed MCPs, connection status, accounts, catalog tool counts). Since no output schema exists, this textual enumeration is sufficient for an agent to understand the tool's return 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?

The tool accepts zero parameters, and the schema coverage is trivially 100%. With no parameters to document, the description does not need to add parameter-level detail; 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 'Returns' with the resource 'current toolkit state' and enumerates the components (installed MCPs, connection status, accounts, catalog tool count). This clearly identifies what the tool does and implicitly distinguishes it from action-oriented siblings like 'authenticate' or 'connect', though it does not explicitly name alternatives.

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 only states what the tool returns and provides no guidance on when to call it or how it compares to sibling tools. There is no mention of use cases like 'check status before connecting' or exclusions, leaving the agent to infer when to use this tool.

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