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

With no annotations, the description carries the full behavioral burden and it does disclose the read-only, enumerative nature plus the returned fields. However it says nothing about permissions, whether the list is filtered by the caller's account access, or any rate/volume constraints, so an agent cannot tell how complete the listing will be.

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

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

Two short sentences, front-loaded with what the tool returns and followed immediately by when to reach for it. Every clause earns its place with 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?

No output schema exists, so the description usefully enumerates the returned fields, and for a zero-parameter read tool there is little else to specify. It is close to complete, though an agent still lacks any statement about scoping or authorization of the returned accounts.

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 the baseline is 4. The description does not need to explain any input semantics and correctly introduces none.

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+resource ('Lista las cuentas bancarias disponibles') and enumerates the fields returned (banco, tipo, moneda, numero), which is more than a tautology of the title. It implicitly separates itself from 'movimientos' by positioning itself as the prior step, but it never names any sibling tool explicitly.

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?

'Util como primer paso para saber que cuentas existen antes de pedir movimientos' gives clear usage context and even points at the natural follow-up action. It does not state exclusions or reference the actual sibling names ('saldos', 'saldos_historicos', 'movimientos'), so routing is implied rather than 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?

With no annotations, the description carries the load and does disclose real behavior: it auto-discovers accounts, defaults to a summary (per-account totals plus the 25 most recent), and warns about volume for long ranges. It omits permissions/rate-limit context, but the default-vs-detail behavior is well covered.

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 tight sentences, front-loaded with the resource and scope, then the default behavior, then the caution. Every clause 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?

No output schema exists, yet the description explains the return shape (totals per account plus 25 most recent) and the volume tradeoff, so an agent can call it correctly. Minor gaps remain around the tipo enum semantics and any account filtering, but the essentials are present.

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

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

Schema coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema for 'detalle' by explaining what the default summary actually contains and when switching to detail is unwise. The 'tipo' enum and its default are left entirely to 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+resource: transactions ('movimientos') across all accounts within a date range, and notes it auto-discovers accounts. Clear enough to distinguish from siblings like saldos or listar_cuentas, though it never names them explicitly.

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 a concrete condition for using the detail mode: request detail only for short ranges because long ranges return thousands of records. It does not, however, contrast with sibling tools (saldos, saldos_historicos) to help the agent pick between them.

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

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

No annotations exist, so the description carries the full burden. It discloses a genuine behavioral constraint (64-day maximum range) and the scope of returned balances (three account types), which is real, non-obvious context. It stops short of richer disclosure like read-only nature or response shape, keeping it out of the top band.

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 tight sentences, front-loaded with the resource and balance types, then the range limit and the alternative. Every clause earns its place with 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?

For a three-parameter, non-mutating query with no output schema, the definition covers the essential constraints and routing guidance. The only gap is the absence of return-shape hints, which is acceptable given the tool's 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?

Schema description coverage is 100%, so desde, hasta and moneda are already documented with format and enum. The description only adds the 64-day limit that binds the date parameters, which is mild value beyond the schema and consistent with the baseline 3 when the schema does the heavy lifting.

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 (current balances across all accounts) and even enumerates the three balance types (contable, operativo, proyectado). It explicitly contrasts itself with the sibling saldos_historicos, so an agent can route correctly 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?

Names the alternative (saldos_historicos) together with the exact condition that selects it: date ranges longer than 64 days. The optional range for this tool is stated with its bound, leaving nothing to inference.

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?

With no annotations, the description carries the burden and discloses meaningful behavior: automatic splitting into 60-day chunks due to the API's 64-day limit, unified series return, and summary vs. day-by-day modes. It still omits read-only status, auth requirements, and error behavior.

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 the purpose, then the chunking behavior, then return-mode guidance. Every sentence is useful and there is no redundant 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?

Without an output schema, the description does explain that it returns a summary per account by default and a daily series when detalle is true. It also explains automatic chunking, but lacks detailed output fields, auth, and error-handling context.

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 already documents all three parameters. The description restates the detalle meaning and adds that it returns the day-by-day series, but adds no syntax or constraints 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 resource (saldos diarios) and scope (rango de fechas largo), so the agent knows this retrieves historical daily balances. However, it does not explicitly differentiate this tool from the sibling saldos or movimientos 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?

The phrase 'rango de fechas largo' implies when to use this tool, and 'usar detalle para la serie dia por dia' guides parameter choice. There is no explicit when-not guidance or comparison to sibling tools such as saldos or movimientos.

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