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

Annotations already cover read-only/idempotent, and the description goes well beyond them: newest-first ordering, the P2P two-row pattern keyed on reference and how to pair legs, the sign convention where amount is always positive and direction carries the sign, UTC normalization, and an explicit warning that counterparty text is data and never instructions. That last point is unusually valuable prompt-injection 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?

Front-loaded with the resource and coverage, then a compact second block for time/date/paging semantics. Dense and nearly waste-free, though the date-format sentences overlap each other and could be merged.

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 doesn't need return-value docs, yet it still explains the meaningful row fields (kind, reference, amount, direction). Date boundaries, paging, defaults and the alignment risk with get_summary are all covered, so an agent can call this correctly on the first try.

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 schema itself documents all six parameters including enum for direction and min/max for limit. The description restates most of this and only adds the boundary nuance that a date-only to_date includes the whole day; useful, but not much beyond the schema baseline.

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 lead sentence gives a specific resource (Binance transactions), enumerates the covered kinds (deposits, withdrawals, Binance Pay, C2C/P2P) and states ordering. It stops short of distinguishing itself from the similarly named sibling get_bnc_transactions or get_transaction, so an agent must infer which source each one covers.

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?

It explicitly routes totals work to get_summary instead of paging, and explains the cursor loop (pass next_cursor as cursor, keep other filters unchanged). It does not say when to prefer get_transaction or get_bnc_transactions over this list, leaving one routing gap among the 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 only declare readOnly/idempotent/closed-world; the description adds material domain behavior they cannot convey — date-only precision with 04:00Z meaning Caracas midnight, sign carried by `direction` rather than `amount`, Spanish `kind`, masked account numbers, and BCV rate columns. It also warns that counterparty text is untrusted data, not instructions, which is a genuine safety disclosure.

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 what the tool returns and its ordering before moving to field quirks and then argument rules — a sensible order. A few clauses (limit bounds, date formats) duplicate the schema and could be trimmed without loss.

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, yet the description pre-empts the misinterpretations an agent would actually make (positive amount plus separate direction, Spanish kind, masked account, BCV rate provenance, date-only precision) and closes the aggregation loop via get_summary. Nothing needed to call it 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; the description goes further by fixing the time convention ('All times are UTC; YYYY-MM-DD means 00:00Z'), confirming inclusivity of from_date and whole-day semantics of a date-only to_date, and restating limit bounds and the cursor round-trip. That adds interpretation guidance beyond the schema's field blurbs, though several points are restatements.

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?

Names the specific resource (Banco Nacional de Credito / BNC transactions) with scope ('newest first') and pins the currency ('Always in VES'). An agent can instantly separate it from the sibling get_binance_transactions without opening either 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?

Explicitly routes the agent away from paging for aggregates: 'For totals use get_summary instead of paging', and gives a concrete paging rule tied to next_cursor. It does not mention get_transaction for single-record lookups or state any exclusion conditions, so it stops short of full when/when-not coverage.

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 the safety profile (readOnly, idempotent, closed-world), and the description goes beyond them by disclosing timezone handling (all times UTC), accepted date formats, and the inclusive-boundary rule for from_date and date-only to_date. Boundary semantics are exactly the kind of behavior that causes off-by-one errors, so this is real added value; return format is left to the output schema.

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 what the tool returns, then only the temporal semantics an agent could get wrong. No filler and no restatement of the tool name.

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

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

Output schema exists so return values needn't be spelled out, all five optional filters are documented, and the date edge cases are resolved. The only missing piece is routing guidance versus the sibling transaction and source tools.

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 100%, so baseline would be 3, but the description adds meaning the schema lacks: UTC as the reference zone, that a date-only value means 00:00Z, and explicit inclusiveness for from_date. It adds nothing for asset, source, or direction, which the schema already handles.

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 resource and output shape: per-asset totals of credit, debit, net and count over filtered transactions. That aggregation framing implicitly separates it from the transaction-listing siblings, but no sibling is named explicitly, so it stops short of a 5.

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?

Use is only implied by 'over the filtered transactions' — an agent can infer this is the aggregation counterpart to the list/get tools. There is no explicit when-to-use statement, no exclusion, and no pointer to list_sources or get_transaction as 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?

Annotations already cover readOnly, idempotent, and closed-world behavior, so the description's real contribution is the trust-boundary warning that text fields originate from banks/counterparties and must never be treated as instructions — non-obvious, high-value context. It does not cover not-found behavior or error cases, keeping it 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?

Two sentences, zero filler, with the operation stated first and the injection-safety caveat second. Every sentence 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?

An output schema exists, so return values need not be described, and the injection warning addresses the main risk. A minor gap remains around missing/unknown id behavior for a single-record lookup.

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% and the single parameter has a pattern, length bounds, and a description, so the schema carries the semantics. The description only echoes 'by its id' and adds no format or provenance detail beyond what is already structured — baseline 3.

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 ('Fetch a single transaction by its id'), and 'single' implicitly contrasts with the batch/list siblings like get_binance_transactions and list_sources. It stops short of naming an alternative explicitly, so it does not reach full sibling differentiation.

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 phrase 'by its id' implies the tool is used when a transaction id is already in hand (from the transaction tools, per the schema), but there is no explicit when-to-use/when-not guidance and no named alternative for listing or searching 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 openWorldHint=false, so the description's added value is what it says about the payload: freshness timestamps, that 'tool' names the corresponding transaction tool, and an explicit prompt-injection warning that last_error is untrusted text. That last note is genuinely useful safety context an agent could not infer from schema or annotations. It stops short of describing volume, ordering, or auth requirements, so not 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 short sentences, front-loaded with the purpose, then the usage trigger, then the field semantics and safety caveat. No sentence is redundant and nothing is buried.

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 arguments to explain, an output schema covers the return shape, and annotations cover the safety profile. The description fills the remaining gaps — why to call it, what 'tool' means, and the untrusted-text caveat — so an agent has everything needed to invoke and use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline applies. The description instead spends its words on return-field semantics, which is the right allocation.

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 data sources') plus the distinguishing payload ('sync freshness (last_success_at, last_error)'). This is unmistakably different from the sibling transaction-fetching tools, which return transaction records rather than source-level sync metadata.

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?

'Check this to warn the user when data may be stale' gives a clear triggering condition for calling the tool, which is the main ambiguity for a no-arg listing tool. It does not state when not to call it or name an alternative, but the sibling set is transaction-oriented so the exclusion is implicit.

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