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

Annotations only carry generic hints (readOnlyHint=false, idempotentHint=true, destructiveHint=false). The description discloses what those hints cannot: the partial-update behavior (omitted/empty fields retain their values), the joint-account permission model, and the side-effect profile of writing balance (direct overwrite with no effect on invoice or transaction history). No contradiction with any annotation.

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 dense sentences, each carrying distinct information: the core update contract, the permission/deletion caveat, and the balance warning. The core purpose is front-loaded, and there is zero filler or restatement of schema 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?

With an output schema present (return values covered) and annotations covering the safety/idempotency profile, the description supplies the remaining invocation-critical facts: who has permission, what partial updates do, and how balance behaves. Nothing an agent needs to call update_account 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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by establishing the cross-cutting partial-update rule that applies to all 7 optional parameters (omitted means unchanged), and by flagging balance as the semantically dangerous parameter. The schema describes each field individually, but the tool-level description clarifies the omission contract and the balance pitfall at the right abstraction level.

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 states a specific verb+resource — 'Atualiza campos de uma conta existente' (updates fields of an existing account) — with the crucial partial-update contract added. Combined with the sibling set containing create_account/delete_account and many update_* tools, the phrase 'conta existente' and the explicit pointer to delete_account clearly distinguish this tool from its 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?

The description explicitly states who may call it ('Tanto o dono (OWNER) quanto membros (MEMBER) de uma conta conjunta podem chamar'), carves out an exclusion with the alternative named ('para excluir a conta, porém, só o dono pode (veja delete_account)'), and warns that editing balance 'não é o mesmo que registrar uma transação de ajuste', routing the agent away from this tool when a transaction adjustment is intended. Full when/when-not guidance.

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