Reporte

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real value beyond that with the caveat that values are as stored in each cell and that some bulletins express them in thousands with Excel formatting, plus the note that the response returns the sheet list. It does not address row-by-row paging or what happens when the default limit is hit, which for a raw reader is the one behavioral detail left open.

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 action, then the usage gate, then parameter guidance, all in three compact sentences with no filler. The density is largely justified, though packing the fallback rule and the parameter glossary into continuous prose makes it slightly harder to scan than a short bulleted form.

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 described, and the tool is a read-only bulletin reader whose main risk (unit/scaling) is proactively flagged. However, with 5 parameters and zero schema descriptions, leaving 'limite' and 'periodo' entirely unexplained means the agent cannot know how to control row volume or period selection before calling.

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 full burden, and it explains only two of five parameters: 'filtro: palabras que debe tener la fila' and 'hoja: nombre de la hoja; por defecto la primera'. 'codigo' is only implicitly glossed via 'código de listar_reportes', while 'limite' and 'periodo' are never mentioned at all, and the interplay of 'filtro' with 'limite' (default 40) is not clarified.

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?

Uses a specific verb and resource: 'Lee cualquier boletín de la SBS fila por fila, con la columna (A, B, C...) de cada celda', which tells the agent this is a raw, cell-level reader rather than an aggregator. Concrete bulletin codes (B-2201, B-2340, FP-1201) anchor the scope, but differentiation from siblings is left mostly implicit through the fallback framing rather than an explicit contrast with e.g. indicadores or ranking.

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 an explicit selection rule: 'Úsenla cuando ninguna otra herramienta tiene el dato', which is a genuine when-to-use gate rather than a vague hint. It also routes to listar_reportes for discovering 'otro código', but it never states which sibling would already carry balances or liquidez, leaving the agent to infer when the fallback condition is actually met.

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