Synci

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

Annotations already carry readOnly/idempotent/non-destructive, so the safety profile is covered. The description still adds non-obvious semantics beyond them: `as_of` is a sync time that can lag transactions, and a negative CLOSING_BOOKED on a credit account means amount owed rather than overdrawn. It does not cover auth, pagination, or rate limits, keeping it just below a 5.

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 tight sentences, no filler; the snapshot scope leads, the staleness caveat follows, and the investment-account redirect closes. Every sentence carries distinct, actionable 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?

Given an output schema exists, the description is not obligated to explain return fields, yet it does so only where agent behavior changes (staleness caveat, negative credit balance, accounts with no snapshots). Nothing needed to invoke or interpret the tool correctly is missing.

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 100% with a single, well-documented `account_id`, so the schema already does the work and the baseline is 3. The description's added value is about returned snapshot fields rather than parameter syntax, so it adds nothing parameter-level 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?

States a specific verb (get) and resource (balance snapshots) scoped to one account, and enumerates the snapshot types (INTERIM_AVAILABLE, EXPECTED, CLOSING_BOOKED). It also positions itself against the sibling list_holdings for the positions case, so an agent can select it without opening a schema.

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?

Gives explicit when-to-use and when-not: investment/crypto accounts usually have no snapshots, and the agent is routed to total_balance, cash_balance, and list_holdings instead. That is exactly the alternative-routing guidance the dimension asks for.

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 only establish the read-only/idempotent profile, and the description adds substantial non-obvious behavior: balances lag transactions so balance.as_of must be checked, earliest_available_date marks the start of synced history and empty results are a coverage artifact rather than zero activity, and sensitive identifiers are omitted. These are exactly the caveats that would otherwise cause an agent to report misleading totals.

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?

Front-loaded with the core purpose and the field list, then the two IMPORTANT caveats. It is on the long side, but each sentence carries operational consequence (stale balances, coverage gaps, empty investment balance blocks) rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be documented, yet the description still covers the traps an agent must know: stale balance handling, synced-history boundaries, and where investment value lives. Nothing needed to call or interpret this tool correctly is missing.

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 100%, so the baseline is 3, but the description goes beyond the schema by enumerating what the 'lean summary' actually contains versus the 'full record' that verbose:true returns. That concretely clarifies the effect of the verbose flag rather than merely restating it.

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?

States a specific verb and resource ('List the user's connected financial accounts') and immediately scopes it by naming the account types and the lean-summary fields returned. It also distinguishes itself from the sibling list_holdings by redirecting there for positions, so an agent can pick between them without opening schemas.

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?

Gives clear routing guidance: call list_holdings for the positions behind investment accounts, read total_balance/cash_balance for broker value, and use verbose:true for the full record. It stops short of an explicit 'do not use this for X' exclusion, so it is strong context rather than a complete when/when-not statement.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description goes beyond them by disclosing that each connection carries a health status (with enumerated values HEALTHY/FAILING/DEAD) and a consent expiry, which materially informs the agent about the data's operational meaning.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the resource and then the return-relevant details, with zero filler. Nothing could be removed without losing 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?

For a zero-parameter read tool with full annotation coverage and an output schema, the description supplies everything needed to select and call it: the resource, its scope, and the notable returned fields. No gap remains that the structured fields do not already cover.

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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. No misleading parameter claims are made.

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?

States a specific verb (List) and a precise resource (the authenticated user's bank/provider connections), and adds the payload's key dimension (health status). It is clearly distinguishable from siblings like list_accounts, list_holdings and list_transactions, which cover different financial resources.

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 scope phrase 'the authenticated user's' implies the calling context, but the description never states when to reach for this tool versus the sibling list_* tools or any exclusions. Usage is inferable from the resource boundary rather than made explicit.

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

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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the safety profile is not the description's burden. The description usefully adds that bank accounts yield no holdings and that omitting the filter spans all investment/crypto accounts, which is behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and returned fields, then the scoping exceptions. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values needn't be explained, yet the description still names the key fields. With annotations covering safety and the sole parameter fully documented, nothing needed to call this tool correctly is missing.

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 100% for the single account_id parameter, and the description only restates the schema's own meaning ('Optionally restrict to one account'). Baseline 3 applies since the schema carries the parameter semantics.

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?

Specific verb (list) plus resource (investment and crypto positions) and enumerates the returned fields (symbol, asset class, quantity, price, market value, currency). It also draws the boundary that bank accounts have no holdings, which separates it from sibling balance/transaction tools.

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?

Gives clear context: it covers investment/crypto accounts, bank accounts are excluded, and the optional single-account narrowing is stated. It references list_accounts for the id but does not explicitly compare against get_account_balance or list_transactions, so an agent still has to infer the boundary rather than being routed.

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 readOnly/idempotent/non-destructive, and the description goes well beyond them: default lean shape vs verbose raw record, omitted sensitive identifiers (IBAN/account numbers), both booked and pending returned by default with mutable pending amounts, keyset paging with no gaps/overlap, and the warning that a short page is not the end of data. That is unusually rich operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but information-dense and clearly segmented with front-loaded purpose followed by Dates/Coverage/Pagination sections. A few passages restate schema content (limit default, cursor keyset paging), so it is not maximally tight, but no section is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though an output schema exists, the description supplies the domain semantics an agent needs to interpret the rows correctly (is_cash_flow for spending totals, units/price_per_unit for trades, coverage under-reporting risk). Combined with 8 well-documented parameters, nothing material is missing.

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 100%, so the baseline is 3, but the description adds real meaning beyond it: amount sign convention ('negative = money out'), date_field semantics with a worked example, is_cash_flow exclusion rule for spending totals, and the note to ignore prices embedded in description strings. Defaults are largely duplicated from the schema, keeping this short of a 5.

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?

Opens with a specific verb+resource and scope: 'List the user's financial transactions in a date window, newest first, across all account types'. It names the covered account types and distinguishes itself from list_holdings/get_account_balance by framing this as the transaction ledger rather than a snapshot or position list.

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?

Gives strong conditional guidance: when to pass verbose, when to override date_field ('spending in June' means mapped), how to handle partial coverage via meta.earliest_available_date, and how to page. It never explicitly names a sibling tool to use instead, which is the only gap.

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