Banco Digio MCP

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

Annotations indicate idempotentHint=true and destructiveHint=false; the description adds behavioral context such as the presence of a link when no args are given and the distinction between persistent and session-only login. It does not cover error handling or return format, but the key behaviors are disclosed.

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 mostly concise, front-loads the purpose, and efficiently describes two login methods. Minor redundancy ('log in in the browser, copy the access token') could be tightened.

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 one optional parameter and no output schema. The description covers the core functionality and two usage scenarios, making it adequate for an AI agent. Missing details like error responses are minor given the overall clarity.

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 fully compensates by explaining that 'token' is a JWT obtained from browser login, and how to use it for session-only login. This adds crucial meaning beyond the raw schema.

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: authenticating for IDE agents by logging in via browser and using an access token. It distinguishes itself from sibling tools (e.g., openfinance, marketplace) by focusing solely on 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 provides explicit when-to-use guidance: recommending a permanent config-based approach over session-only token pasting. It also explains the two invocation modes (with or without token) and their outcomes.

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. The description adds specific return behavior in two states, providing value beyond 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 concise with two sentences, front-loaded with the main purpose, and contains no unnecessary information.

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?

Despite no output schema, the description fully explains the return values in key scenarios. It is complete for a simple status-checking tool with no parameters.

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 exist in the input schema, so schema coverage is 100%. Baseline score of 4 is appropriate as the description does not need to add 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 specifies the tool returns connection status and URLs, with two distinct scenarios. It distinguishes itself from sibling tools like 'authenticate' by focusing on status rather than performing 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 for checking connection status and provides context on when to expect different outputs. It does not explicitly exclude other tools but the scenarios given help in decision-making.

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?

Describes key behaviors beyond annotations: invoke works even for uninstalled MCPs, returns connect/checkout links for auth/payment, writes require owner/admin permissions, search/describe flag installed status. Annotations are consistent (non-readonly, non-destructive, non-idempotent, open-world). No contradiction.

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 comprehensive but verbose (approx. 200 words). It combines multiple concepts into one block, which may be overwhelming. While all sentences are relevant, a more structured format (e.g., bullet points for each action) would improve 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 complexity (15 parameters, no output schema), the description covers all essential aspects: core actions, when to use each, special cases (auth, payment), permissions, and integration with sibling tools. The agent has enough context to use 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?

Schema has 15 parameters with 0% description coverage. The description adds meaning by explaining the action enum values and tying parameters like mcp_id, tool_id, arguments, immediate to the flow. However, some parameters (limit, query, message) are only implicitly covered. A dedicated param section would improve clarity.

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 marketplace is the official MCP catalog and runtime. It specifies the core flow (search → describe → invoke) and distinguishes itself from external registries by directing the agent to use this tool first. The verb 'discover' and 'run' match the action parameter.

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 on when to use this tool vs alternatives: use this first for discovery, prefer invoke for one-off usage, install for permanent addition. Also covers auth and payment scenarios with clear retry instructions. Distinguishes from sibling tools like report_bug and request_mcp.

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?

Description confirms destructive behavior (annotated as destructiveHint: true) by stating data deletion and unavailability. Adds value by mentioning the returned add_connection_url for reconnection. No contradictions with 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?

Three concise sentences with the main action first, no wasted words.

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?

While the description covers the tool's effect and return value, the missing parameter definition reduces completeness. The simple one-parameter tool could benefit from specifying what 'item' represents (e.g., bank identifier).

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?

Parameter 'item' has no description in schema (0% coverage) and the description does not explain its meaning or expected format. For a tool with a single required parameter, this is a significant 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?

Clearly states the tool revokes Open Finance consent, deletes connection data, and returns a reconnection URL. Distinguishes from sibling tools like openfinance_list_connections or openfinance_force_sync.

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 guidance on when to use vs alternatives, but the specific action of disconnecting a bank is implied by the tool name and description. Lacks explicit when-not-to-use or prerequisite info.

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 fully discloses that it forces a sync, polls up to 60s, returns final status, and handles error states like needs_action and timed_out. It also mentions that fresh data is ready when synced=true. The annotations (readOnlyHint=false, destructiveHint=false) are consistent with a non-destructive update operation.

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 well-structured and front-loaded, but slightly lengthy. However, every sentence adds value, covering action, use case, parameters, return format, and error handling. A minor reduction for verbosity.

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 (force sync, asynchronous waiting, error states) and lack of output schema, the description provides a complete mental model: it explains the return structure (results, errors), key fields (status, executionStatus, lastUpdatedAt, synced), and how to handle errors (needs_action, timed_out). It also mentions alternatives like openfinance_get_item_status for re-checking.

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 explains both parameters in detail: 'items' accepts item_id, connector_id, or connector_name, and omitting it syncs all banks; 'wait' defaults to true (blocking) but can be set false for fire-and-forget. This fully compensates for the lack of schema descriptions.

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 action ('forces a re-sync'), the resource ('connections'), and key behavior ('waits for it to finish'). It distinguishes from siblings like openfinance_get_item_status by noting polling behavior and providing a clear use case.

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 specific when-to-use guidance ('when a balance or transaction list looks stale'), explains what it does NOT do ('without disconnecting/reconnecting'), and describes the optional 'wait' parameter for fire-and-forget usage. It implicitly contrasts with check-status 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?

The description adds significant behavioral context beyond annotations: CREDIT accounts may return a Pluggy error with a warning, and upstream unavailability causes graceful degradation with realtime: false and a warning. These details are not captured by readOnlyHint or idempotentHint.

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 method, then details error cases and response shape. While it is somewhat detailed, each sentence adds value, and the structure is logical. Could be slightly tighter, but overall effective.

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, the description explains the response shape explicitly ({ results: [...], errors: [...] }). It covers all relevant error conditions (CREDIT accounts, upstream failures) and ensures the agent understands the tool's behavior completely.

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 has 0% description coverage for the only parameter, account_ids. The description provides essential semantics: it is an array of 1-50 strings and error handling related to CREDIT accounts and upstream failures. While it doesn't specify ID format, it compensates well 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 clearly states the tool returns a real-time balance payload per account ID via GET /accounts/:id/balance. It specifies the verb 'get' and resource 'account balance', differentiating from sibling tools like openfinance_list_accounts or openfinance_get_accounts_detail.

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 how to use the tool (pass account_ids as an array of 1-50) and describes error-handling scenarios. However, it does not explicitly state when to use this tool versus alternatives for balance retrieval or account 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?

Beyond annotations (readOnlyHint, idempotentHint), description adds batch result shape, provider_incident block with unreliable data warning, and array size constraint. 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?

Two sentences, focused and efficient. First sentence covers main function, second covers batch shape and critical warning. No redundant information.

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 essentials: input, batch shape, special case. But lacks detailed output structure or explanation of 'full account objects'. Without output schema, some ambiguity remains.

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?

Only parameter is account_ids, described as an array (1-50). Adds basic format and constraint but does not explain what account IDs represent (e.g., format, origin). Compensates partially for 0% schema 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?

Description clearly states it returns full account objects with extended creditData per ID, and specifies the HTTP method and endpoint. Distinguishes from sibling tools like openfinance_list_accounts by focusing on per-ID detail.

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?

Explicitly notes to pass account_ids as an array (1-50) and the batch shape. Provides warning about provider_incident. Lacks explicit when-not-to-use, but context implies it's for detailed per-account retrieval.

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 beyond annotations by disclosing batch return shape ({ results, errors }), connector-specific behavior (Pluggy missing paid/status), and nuance that payments[] reflect previous bill's payment. Aligns with annotations (readOnlyHint, idempotentHint, non-destructive).

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?

Description is thorough but front-loaded with core purpose, then adds caveats. Each sentence is informative, though slightly long. No extraneous information; could be trimmed slightly but remains clear.

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, the description fully addresses what the tool returns and critical nuances (batch shape, payment semantics, connector quirks). Covers edge cases and prevents misinterpretation, making it complete for the tool's complexity.

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 coverage, description compensates well: explains that bill_ids is an array, recommends using list_credit_card_bills to discover ids, and hints at batch shape. Could add more detail on array constraints (e.g., non-empty), but sufficient for proper use.

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 returns bill-level detail for one or more credit card bills, specifying the fields (financeCharges, payments) and explicitly distinguishing from individual transactions. It uses specific verb 'Returns bill-level detail' and resource 'credit card bills by id', differentiating from sibling tools like openfinance_list_transactions.

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?

Explicitly instructs when to use this tool (to get bill detail after discovering ids via openfinance_list_credit_card_bills) and when not (do not use to get transactions; use openfinance_list_transactions instead). Provides warning about reconstructing totals and misinterpretation of payments array.

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, destructiveHint=false. Description adds concrete return structure details: object with status, executionStatus, connector metadata, and the bulk return shape { count, items }. 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?

Two sentences with no redundancy. First sentence establishes purpose and values, second explains parameter usage. Perfectly front-loaded and concise.

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 read-only tool with one optional parameter and no output schema, the description fully covers both input scenarios and expected return shapes. No 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?

The only parameter `item` has 0% schema coverage, but the description fully explains its semantics: omitting it returns all banks, passing a value returns one bank. This compensates completely.

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?

Description clearly states it returns bank connection status with specific enum values (UPDATED, UPDATING, LOGIN_ERROR, etc.). Distinguishes two usage modes (bulk vs single bank) which differentiates it from siblings like openfinance_list_connections.

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?

Explicitly instructs when to omit or pass the `item` parameter for bulk vs single bank status. While it doesn't explicitly mention alternatives, the context is clear enough for an agent to decide.

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 it readOnly and idempotent. Description adds that it's a GET endpoint, describes batch processing, and lists return fields, providing operational details beyond 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?

Description is one long sentence but packs all necessary info. Could be broken for readability, but front-loads purpose well. 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?

Despite no output schema, description enumerates many return fields and response shape. Adequate for a detail endpoint with low schema info.

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 description adds meaning: 'Pass loan_ids as an array (1-50)' giving range constraint and batch handling context.

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 returns full loan contract detail by ID, lists specific fields, and distinguishes from sibling tool openfinance_list_loans by explicitly directing use after that list call.

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?

Explicit guidance: 'Use after openfinance_list_loans to deep-dive on a specific contract.' Also specifies batch parameter constraints (1-50 loan_ids) and response shape ({ results, errors }).

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 indicate read-only. Description adds critical context: provider_incident block may cause unreliable data, and each account's name is the legal issuer not the brand. Transparency beyond 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?

Description is somewhat lengthy but every sentence adds value. Front-loaded with main purpose and key usage details. Could be slightly more concise, but structure is logical.

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?

No output schema, but description thoroughly explains response structure (bank, connector_id, balance, etc.) and special cases like provider_incident and credit balance variability. 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 coverage, description fully compensates: explains item parameter usage (omit vs pass) and defines type enum values (BANK as checking/savings, CREDIT as credit card). Adds meaning beyond the minimal schema.

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 accounts for bank connections, specifying types BANK and CREDIT, and lists returned fields (balance, number, type, etc.). It distinguishes between bank brand and issuer name, and differentiates from sibling tools like openfinance_list_credit_card_bills.

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?

Explicitly tells when to omit item (list all banks) vs pass item (single bank). Warns that credit balance meaning is connector-dependent and suggests using openfinance_list_credit_card_bills for standardized amounts. Also notes provider_incident block and advises against presenting unreliable values.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds useful context: caching for the adapter session, single aggregated response (no batch IDs), and the specific fields returned. This enriches understanding beyond 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, no wasted words. All information is essential: what the tool does, caching, field details, language preference, and relationship to sibling. Front-loaded with key action verb '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?

Despite no output schema, the description fully explains the return structure (id, description, descriptionTranslated, parentId, parentDescription). It also covers caching, session scope, and the singleton nature. This is complete for a taxonomy listing 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?

No parameters exist (schema coverage 100%), so baseline is 4. The description doesn't need to add parameter info, and correctly focuses on output structure.

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 returns Pluggy's transaction category taxonomy, specifies it's cached, and details the fields (id, description, descriptionTranslated, parentId, parentDescription). It explicitly links to sibling tool openfinance_update_transaction_category via the categoryId, distinguishing its purpose.

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 notes caching behavior (implying repeated calls are cheap) and recommends descriptionTranslated for pt-BR users. It doesn't explicitly state when not to use it, but the purpose is clear enough given the context of transaction categorization.

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 readOnly, idempotent, non-destructive. Description adds that it returns fields and an add_connection_url for linking additional banks, which is useful context beyond 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?

Single, concise sentence with verb front-loaded. No unnecessary words.

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 and no output schema, the description sufficiently explains the tool's purpose and return fields. Complete for a simple list 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?

No parameters, so baseline score of 4 applies per rubric. No additional parameter info 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?

Description clearly states it returns saved bank connections and lists specific fields (connector_id, item_id, bank name, add_connection_url). Distinguishes from siblings like authenticate, connect, disconnect, etc.

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 guidance on when to use this vs alternatives; usage is implied by the name and description. Does not mention when not to use or specify prerequisites.

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 and idempotentHint=true. The description adds rich behavioral context: payment_status derivation, billing cycle logic, connector asymmetry, open_bill availability conditions, and warning behavior. No contradiction with 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 very lengthy and verbose, containing extensive details on payment status logic and connector behavior. While it is well-structured with bolded terms, it could be more concise. Every sentence adds value, but the overall length reduces quick parsability.

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 (Brazilian Open Finance semantics, payment cycles, connector asymmetry, open_bill opt-in), the description is highly complete. It covers return values, interpretation guidelines, limitations, and warnings. No output schema exists, so the description fully compensates.

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 carries the burden. It explains include_open_bill and batched account_ids in detail. However, page and page_size parameters receive no description, though they are standard pagination. Overall, it adds significant meaning beyond the schema for most 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 clearly states the tool returns closed credit card bills for a CREDIT-type account, listing specific fields and derived data. It distinguishes itself from siblings like openfinance_get_credit_card_bill (singular) and openfinance_list_transactions (itemized purchases).

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 guidance on when to use this tool (bill-level summaries) vs alternatives (itemized purchases via openfinance_list_transactions). It explains the opt-in open_bill parameter, connector asymmetry, and warns against reconstructing totals from transactions.

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, so behavioral transparency is partially covered. The description adds significant value by detailing the error-handling behavior: returns a structured object with total, results, and warning instead of throwing on 403 or other upstream errors. This is beyond annotations and aids agent understanding.

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 efficient, front-loading the core purpose then listing return fields and error behavior in a single sentence. No redundant information; every part adds value. Well-structured for quick parsing.

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 complexity (4 parameters, no output schema) and rich annotations (readOnlyHint, etc.), the description covers return data and error handling adequately. However, it lacks guidance on pagination (page, page_size) and the 'item' parameter (likely a connection identifier). The description is incomplete for an agent to invoke correctly without additional knowledge of the parameter semantics.

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 does not explain any of the four parameters (item, page, type, page_size). The only hint is the list of investment types in the description, which loosely maps to the 'type' parameter's enum values. The description fails to compensate for the missing schema descriptions, leaving parameter meaning largely 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 the tool returns the investment portfolio for a connection, listing specific asset types (FIIs, stocks, ETFs, etc.) and return fields. It uses a specific verb 'Returns' and distinguishes from sibling list tools by focusing on investments portfolio rather than accounts, transactions, or credit cards.

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 connections with INVESTMENTS product enabled but does not explicitly state when to use this tool versus alternatives like openfinance_list_investment_transactions. No exclusions or specific context beyond the product requirement are provided, leaving the agent to infer when it is appropriate.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context by detailing the output fields (quantity, value, netAmount, agreedRate, brokerageNumber, expenses breakdown) and bulk support. This goes beyond annotations without contradiction.

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—two sentences in the first paragraph covering return details, and a second paragraph for usage. Every sentence adds value, with no redundancy. It is front-loaded with the core purpose and then provides context.

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, the description adequately covers return fields and the prerequisite relationship with openfinance_list_investments. It mentions bulk support but lacks detail on pagination parameters (page, page_size) or what happens with invalid investment_ids. Still, it is largely complete for a read-only list 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 compensates by explaining that investment_id is the identifier from openfinance_list_investments and that investment_ids enables bulk execution. It does not describe page and page_size parameters, but these are common pagination parameters with implied 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 states the tool returns movement history for a specific investment position, listing transaction types (BUY/SELL/TAX/etc.). It distinguishes from sibling tool openfinance_list_investments by explicitly stating it should be used after that tool to obtain the investment_id.

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 context: 'Use after openfinance_list_investments to get the investment_id.' It also mentions bulk support with investment_ids, giving clear usage guidance. However, it does not explicitly exclude alternative tools or state when not 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.

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds that multiple connections are queried sequentially with rate-limit spacing and returns per-connection results/errors, providing useful behavior details beyond 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?

Three concise sentences, front-loaded with the purpose. Every sentence adds value with 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?

Given the simple input (one optional parameter) and no output schema, the description explains input, behavior, and output format sufficiently. Annotations cover safety. It is complete for the tool's complexity.

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%, but the description fully explains the `items` parameter: it is an array of connection selectors (item_id, connector_id, or connector_name) and that omitting it lists all banks. This adds complete meaning beyond the bare schema.

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 lists loan contracts per bank connection, using a specific verb ('lists') and resource. It distinguishes from sibling tools like openfinance_list_accounts by focusing solely on loans.

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 how to use the tool: provide `items` for specific connections or omit for all. It mentions sequential querying with rate-limit spacing, but does not explicitly compare to alternatives or state 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?

Despite annotations already indicating readOnly, idempotent, and non-destructive, the description adds extensive behavioral context: connector-specific inconsistencies (e.g., Nubank sparse billId), pagination behavior (auto-pagination vs manual), error handling (returns error object), detail level effects, and provider incidents. No contradiction with 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 very long and could be more concise, but it is front-loaded with the main purpose and organized logically. Given the complexity and lack of schema descriptions, the verbosity is justified, but some sentences could be trimmed or reformatted for better scanning.

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 all necessary aspects: purpose, usage guidelines, behavioral nuances, parameter semantics, error handling, and edge cases like provider incidents and bulk support. No missing elements 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?

With 0% schema description coverage, the description fully compensates by detailing each parameter: from/to (ISO format), search_queries (case-insensitive substring OR), detail (compact/rich/raw with full explanation), page/page_size (pagination), account_id (required), account_ids (bulk support). Also explains the response structure and account echo block.

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 returns transactions for bank accounts of type BANK or CREDIT. It distinguishes itself from siblings by noting it is the ONLY way to get itemized transactions for credit cards and contrasts with openfinance_list_credit_card_bills for bill totals and openfinance_list_accounts for statement dates.

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 when-to-use (itemized transactions) and when-not-to-use (do not sum transactions by billId; use openfinance_list_credit_card_bills for totals). Gives alternatives like openfinance_get_item_status for zero results. Also includes guidance on filtering, pagination, and handling of CREDIT PENDING vs POSTED.

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 annotations (readOnly, idempotent, non-destructive), describes caps at 5000 transactions per account with truncation flag, and provider_incident block for incomplete 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?

Thorough but slightly verbose; uses bold for emphasis and logical flow, though some repetition could be trimmed.

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 return format (compact summary vs raw rows), per-account breakdown, truncation, provider incidents. No output schema but description compensates fully.

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 coverage, description fully explains all 7 parameters: valid values for 'item', ISO date format for 'from'/'to', granularity default and behavior, detail options, and type filter.

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?

Clearly states it performs consolidated cash-flow analysis for a bank connection, resolving accounts internally. Distinguishes from sibling tools by noting no need to call openfinance_list_accounts first.

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?

Explicitly describes when to use (annual/monthly analysis, cash flow, top expenses) and when to use different granularity/detail settings. Provides context for omitting 'item' to analyze all banks.

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?

Discloses that the tool reads a public status page (non-destructive, idempotent) and lists return fields: global indicator, degraded components, open incidents, and flagging affected banks. No contradictions with 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?

Three sentences, front-loaded with purpose. Efficient but could be slightly more concise; still 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?

Given no parameters and no output schema, the description fully covers what the tool does, when to use it, and what it returns (global indicator, components, incidents, affected banks). Complete for a zero-parameter 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?

No parameters exist, so baseline 4 applies. The description compensates by explaining the tool's input-less nature and what it returns.

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 checks the LIVE operational status of the Open Finance provider via its public status page. It differentiates from the sibling tool 'openfinance_get_item_status' by focusing on provider-side health versus connection status.

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?

Explicitly describes when to use: when data is incomplete or stale even though a connection shows updated, and helps differentiate provider-side problems from connection issues. Provides actionable 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?

Discloses that it honors the user's plan (PF hides PJ), surfaces caveats for credential connectors, and never dumps the full catalog without keywords. Adds context beyond readOnlyHint and idempotentHint annotations without contradiction.

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?

Five sentences, each adding value. Could be slightly tighter but is well-structured with key information front-loaded. 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?

No output schema, but description thoroughly explains return values (connector id, access, audience, connections, accounts conditionally, connect_url, caveat) and edge cases (missing keywords, plan restrictions). Sufficient for an AI 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 schema description coverage at 0%, the description compensates by explaining keywords[] as required search terms and include_accounts for returning accounts. Lacks default values but provides sufficient meaning for correct invocation.

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?

Clearly states it searches bank connectors by name, returns connector details including id, access type, audience, linked connections, and connect_url. Distinguishes from siblings by positioning as a pre-connection step.

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?

Explicitly instructs to call this before connecting, mentions that keywords[] is required, and advises preferring Open Finance connectors due to caveats. Provides clear when-to-use and when-not-to-use 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?

Discloses key behavioral traits: recategorizing creates a Category Rule that affects future similar transactions (case-insensitive exact match). Describes batch response shape with { updated, results, errors } and per-item error handling. Adds significant context beyond annotations, which only indicate non-read-only, non-destructive, non-idempotent.

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 paragraph that front-loads the purpose. Contains multiple key pieces of information (param structure, side effect, batch response) without excessive verbosity. Could be slightly more structured (e.g., separate sentences), but overall efficient.

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 all necessary aspects for correct usage: purpose, parameter explanation, behavioral side effects, batch response shape. No output schema exists, but the description compensates by detailing the response. An agent can confidently invoke this tool based on the description.

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 has 0% description coverage, but the description fully explains the items parameter structure (array of objects with transaction_id and category_id). Explains that transaction_id comes from openfinance_list_transactions and category_id from openfinance_list_categories, adding meaning beyond the schema.

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?

Clearly states the tool corrects the category of one or more transactions. Explicitly mentions the HTTP method (PATCH) and endpoint. Distinguishes from sibling tools like openfinance_list_transactions and openfinance_list_categories by specifying where the IDs come from.

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 clear instructions on how to use it (pass items as an array of objects with transaction_id and category_id). Explains the effect: overrides automatic categorization and creates a Category Rule for future transactions. States it should be used to fix miscategorized transactions. Lacks explicit when-not-to-use or alternatives, but the context is sufficient.

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 indicate idempotentHint=true and destructiveHint=false, so the description's mention of 'report' implies a safe write operation. The description does not add further behavioral detail beyond what annotations provide, but there is no contradiction. Adequate, but could elaborate on outcome (e.g., ticket creation).

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, front-loading the purpose and providing a key usage instruction. Every sentence adds value with 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?

With no output schema and 0% schema description coverage, the description is minimal. It does not cover return behavior, authentication, or what happens after reporting. For a feedback tool, this lacks necessary context for an agent to understand the full impact.

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%, meaning none of the 3 parameters have descriptions. The description only mentions 'conversation array' but does not explain the 'context' or 'message' fields or their formats. The description fails to compensate for the lack of schema descriptions.

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: report a bug, missing feature, or send feedback. It uses specific verbs and resources. Among siblings focused on finance and authentication, this tool's purpose is distinct.

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 a clear context for use (bug/feature/feedback) and a specific instruction to include the conversation array for reproduction. However, it does not explicitly state when not to use or compare to alternatives, though siblings are unrelated.

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, destructiveHint=false. The description adds that the output is version info, but no further behavioral traits beyond what annotations cover. 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?

Single sentence, no wasted words. Front-loaded with the action and resource. Perfectly concise for the tool's simplicity.

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?

Low complexity, empty schema, annotations cover safety. No output schema, but description adequately states what is returned. A bit sparse on return format, but acceptable given simplicity.

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 exist (schema coverage 100% empty). Description doesn't need to add parameter info. Baseline for 0 params is 4.

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 shows 'MCP platform and adapter versions'. The verb 'Show' and resource 'versions' are specific. This distinguishes it from sibling tools which are finance-related or 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?

No explicit alternatives or when-not-to-use guidance, but the tool's purpose is self-evident. In context of siblings, it's the only version tool, so usage is clear. Lacks exclusion criteria.

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, destructiveHint=false. The description adds specific behavioral context about what data is returned (installed MCPs, connection status, catalog counts), 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 sentence that front-loads the purpose and key output details. Every part is informative and there is no 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 output schema, the description fully explains what is returned (installed MCPs, connection status, catalog counts). For an info tool with zero parameters and rich annotations, this is 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 tool has zero parameters and schema coverage is 100%. With no parameters, the description doesn't need to add parameter semantics. Baseline 4 is appropriate.

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 current toolkit state including installed MCPs, their connection status, and catalog tool counts. It uses a specific verb ('Returns') and distinguishes itself from sibling tools like '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 it is for getting an overview of the toolkit state, but does not explicitly state when to use it versus alternatives. No exclusions or when-not-to-use guidance is provided.

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