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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, so the description does not need to repeat them. It adds valuable behavioral context by warning that the upstream requires dt_ano_aviso and specifically disallows a date-range window. This prevents an otherwise plausible misuse given the typical date-range filtering in sibling list tools.

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 deliver the purpose, endpoint, and the single most important invocation constraint. The required-parameter warning is front-loaded and emphasized with bold, leaving no redundant content.

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 tool with nine parameters, the schema documents every parameter with descriptions, an output schema exists, and annotations cover safety semantics. The description supplies the one non-obvious call-level constraint that is not fully explicit in the schema context. Nothing essential for invoking 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 description coverage is 100%, so the baseline is 3. The description adds one meaningful clarification beyond the schema: dt_ano_aviso must be a full year (e.g., 2024), not a date window. This directly prevents a common mistake even though the schema already labels the field as the announcement year.

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 opens with a specific verb and resource: 'Lista compras sem licitação (dispensa/inexigibilidade) do regime legado.' This clearly identifies the tool as a legacy-regime listing operation and distinguishes it from bidding, pregao, RDC, and item-level sibling tools. The parenthetical explicitly scopes the semantics to dispensa/inexigibilidade, so the agent knows exactly what kind of purchases are returned.

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 provides clear context: this is for legacy-regime purchases without bidding. It also flags the critical upstream requirement (dt_ano_aviso as a full year, not a date window). It does not name alternatives or state when not to use it, but the legacy-regime qualifier is enough context to route the agent correctly among siblings.

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