read_drawing

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

With no annotations, the description carries the full burden. It discloses that por_capa=true requires a slow COM sweep (tens of seconds), which is a useful performance warning. It also signals a read-only intent via 'LEER ANTES DE ESCRIBIR' and lists the exact data returned. It does not explicitly state 'does not modify the drawing' in a direct sentence, but the read-before-write phrasing implies it. The behavioral context added is valuable.

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?

The description is well-structured: it leads with a clear purpose statement, then adds usage guidance and parameter-specific details. It is a bit verbose, but every sentence adds value (purpose, timing, alternative, performance warning). It is not overly long and avoids unnecessary wording.

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?

The tool has an output schema, so return values need not be explained. However, with three parameters and 0% schema coverage, the description leaves two parameters undefined, which is a notable completeness gap. It does provide a clear primary use case and an alternative for layer-specific queries, but the missing parameter semantics reduce the overall context. Adequate for the core purpose but not fully complete.

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 description coverage is 0%, so the description must explain all parameters. It only explains 'por_capa' ('agrega el conteo por capa') and mentions its performance cost. It does not explain 'max_scan' or 'top_layers' at all, leaving agents without any clue about their meaning or default behavior. This is a significant gap for a tool with three undocumented parameters.

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 clearly states the tool provides an 'overview of the active drawing' with units, extension, entity counts, block definitions, and XREFs. It uses a specific verb ('read'/'panorama') and resource ('active drawing'), and distinguishes itself from query_entities by noting it is a global overview. However, it does not explicitly differentiate from the sibling get_drawing_info, which may overlap.

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 says 'Es el primer paso antes de tocar cualquier plano' (it is the first step before touching any plan), which clearly tells when to use it. It also provides an explicit alternative: 'Para preguntar por una capa puntual usa query_entities(layer=...)' and warns about performance implications when por_capa=true. This is strong contextual guidance.

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