save_document

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds the concrete consequence (overwrites the current file), the gating requirement (confirm=true), the failure behavior without confirmation (ok=false with a preview), and a precondition refusal. That is meaningful detail beyond the structured fields.

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?

Front-loads the destructive warning, then when-to-use, precondition, parameter note, and a concrete call example. All sections are functional, though the labeled blocks and example make it longer than strictly necessary for a one-parameter tool.

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 destructive single-parameter mutation with an output schema present, the definition covers the safety profile, trigger condition, precondition failure, and confirmation gating. An agent has everything needed to call it correctly without opening the schema.

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 single 'confirm' parameter has 0% schema description coverage, so the description must carry it — and it does: it states the parameter is required in practice to proceed and what happens when it is absent (ok=false plus preview). It stops short of explaining the preview payload itself, though the output schema covers returns.

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 and resource with scope qualifier: 'Salva o desenho ativo POR CIMA do arquivo atual' (saves the active drawing over the current file). The overwrite semantics and destructive nature immediately separate it from adjacent tools like dxf_export or plot_to_pdf.

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?

Explicit 'QUANDO USAR: só quando o usuário pediu para gravar' gives a clear trigger condition, and it names a refusal case (unnamed drawing, never saved) plus the remediation (use SAVEAS in AutoCAD). Nothing about when to invoke is left to inference.

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