update_block_attributes

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

Beyond the destructiveHint=true annotation, the description discloses that overwriting an existing value or touching more than one block without confirm returns ok=false with a preview, and that a single Ctrl+Z reverts everything. This adds real operational context (guard conditions, preview-on-failure, reversibility) that annotations alone do not convey.

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-loaded with purpose, then clearly sectioned into when-to-use, safe-flow, and parameters, so scanning is easy. Slightly repetitive in restating the parameter list and then an example, but every block is informative rather than padding.

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 5-parameter mutation with nested filter objects and an output schema, the description supplies everything an agent needs: targeting logic, safety gating, overwrite semantics, undo behavior, and per-parameter format. Return values are correctly left to the output 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?

Schema coverage is 0%, so the description carries the full burden and does so: it explains attributes as a {TAG: value} map where '' clears a value, handle as a hex string, filter with a concrete nested example (block_name/layer/where), and the roles of dry_run and confirm. This fully compensates for the absent schema descriptions.

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 opening sentence states a specific verb (Altera/muda) and resource (atributos de bloco) and immediately scopes the two targeting modes: single block via handle or multiple via filter. An agent can distinguish this from read_block_attributes or dxf_modify_entities without opening any schema.

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?

A dedicated 'QUANDO USAR' clause names the concrete tasks (corrigir/preencher TAG, TIPO, LINHA) and an explicit safe workflow (dry_run first, then confirm=true) with the failure condition spelled out. No alternative is left to inference for the agent.

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