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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: the previous text is preserved in an internal JusPronto history that the connector cannot yet read, and the summary becomes visible office-wide. The 20k character ceiling is restated but the overwrite/visibility consequences are the valuable additions.

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 sentences ordered purpose → when to use → limits and side effects, with the payoff ('volta instantâneo') front-loaded. The parenthetical about unreadable history is slightly verbose but still earns its place by preventing a wrong assumption.

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 two-parameter write tool with full annotations and no output schema, the definition covers trigger, scope of effect, size limit, and overwrite/history behavior. The only real omission is what a successful call returns (a confirmation or stored id), which is minor given the tool's simplicity.

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% and both parameters carry their own descriptions, including how to obtain processoId via buscar_processos, so the baseline is 3. The description only repeats the 20k character limit already in the schema and adds no new meaning about either parameter.

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 names a specific verb ('Grava') and resource ('o resumo que você compilou do processo'), plus the write scope ('para o escritório inteiro reutilizar'). The line 'o próximo "resuma o processo" volta instantâneo' implicitly separates this persistence step from the summarization sibling (resumo_processo), so an agent can tell the two apart.

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 gives concrete triggers: 'no fim de uma leitura longa' or 'quando o advogado pedir para registrar o estado do caso'. That is clear when-to-use guidance, though it names no explicit when-not condition or alternative tool for the case where a summary already exists.

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