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

Goes well beyond the readOnly/destructive annotations: discloses authorization (same read access as the screen, interns included, refusal when no eligible user), pagination (20 per page with cursor), totals spanning all pages under the declared filters, and the valor vs valorPago accounting rule. It also enumerates the write operations it will never perform, which is meaningful safety context even with destructiveHint=false.

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?

A single dense paragraph, front-loaded with purpose and filters, followed by return shape, semantics, access rules, and exclusions in a logical order. Nearly every sentence carries distinct information, though the sentence count and clause density make it heavier than necessary.

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 6-parameter, nested-schema, filtered read tool with an output schema, the description covers the remaining burden: auth model, refusal case, pagination/cursor contract, total-scope semantics, and out-of-scope operations. An agent has enough to call it correctly without guessing.

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?

With only 33% schema description coverage, the description compensates well: periodo is defined as due-date based, inclusive, in Brasília time; situacao values get concrete definitions. It adds no gloss for clienteId, processoId, or the tipo enum values, which are largely self-describing but still undocumented in 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 ("Consulte lançamentos e totais do escritório") and enumerates the exact filter dimensions (period, situacao, clienteId, processoId, tipo). It also fences the boundary by naming what it does not touch (comissões, repasses, baixa/cobrança), so an agent can separate it from the other 30+ siblings.

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 explicit behavior when no filter is supplied ("Sem filtro, consulta todos") and disambiguates the two easily-confused enum values, PENDENTE vs VENCIDO. It lacks an explicit "use X instead when..." pointer, but no sibling tool covers the financial domain, so there is little to route to.

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