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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context by stating the return format: 'Retorna lista paginada de feriados com nome, data (DD/MM/YYYY), tipo, descrição e indicador bancário (FEBRABAN)' (returns paginated list of holidays with name, date, type, description, and FEBRABAN bank indicator). However, it does not disclose potential error behavior, auth requirements, or the mechanics of pagination (e.g., page parameters). Still, it goes beyond the schema by revealing the output structure.

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 compact and front-loaded, leading with the core purpose in the first sentence. It avoids restating the schema in full, instead providing a high-level overview and then directing users to specialized tools. Every sentence earns its place, and the length is ideal for a query tool with multiple filters.

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 has 7 parameters, no required fields, and no output schema, the description provides a solid overview of both input and output. It explains the return fields (name, date, type, description, FEBRABAN indicator), pagination, and where it fits relative to sibling tools. It lacks explicit mention of pagination controls or common error conditions, but for a general-purpose search tool, it covers the essential context needed for an AI agent to select and invoke 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 schema description coverage is 100%, so the baseline is 3. The description adds a small amount of value by summarizing filterable attributes ('Pode filtrar por data, tipo, estado (UF), cidade (código IBGE), ano e mês'), which helps users parse which parameters are relevant. However, it does not add meaning beyond the schema's already-detailed property descriptions, such as the relationship between month and ano (which is already in the schema). Therefore, a 3 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's purpose: 'Busca feriados brasileiros com filtros flexíveis' (searches Brazilian holidays with flexible filters). It also explicitly distinguishes itself from specialized siblings by noting that for more specific searches, specialized tools like feriados_nacionais and feriados_por_estado should be preferred. This prevents ambiguity.

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 explicitly states when to use this tool: 'Use esta tool para consultas gerais quando precisar filtrar por múltiplos critérios ao mesmo tempo' (use for general queries when filtering by multiple criteria at once). It also provides clear alternatives: 'Para buscas mais específicas, prefira usar as tools especializadas' (for more specific searches, prefer the specialized tools). This contrasts with sibling tools and offers actionable guidance.

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