extract_attributes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that the tool 'Entra en XREF' (enters XREFs), filters by tag signature because it is the 'unico confiable' for dynamic blocks, has a time budget ('presupuesto de tiempo'), and returns 'parcial=true' on timeout, warning that the table is 'INCOMPLETA' and should not be treated as a total computation. This is exceptional transparency about side effects and edge cases.

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 four sentences, front-loaded with the main purpose, then adding conditional usage and a critical warning about partial results. Every sentence carries information and no fluff. It is concise yet dense with actionable guidance.

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?

Given the tool's complexity (9 parameters, no annotations, no schema descriptions), the description covers the essential behavioral context: what it extracts, the XREF scope, the tag filtering rationale, the zone-based usage, and the time-budget behavior with partial results. The output schema exists, so not detailing the return table is acceptable. This description is robust enough for an agent to select and invoke the tool correctly.

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?

With zero schema description coverage, the description compensates well for key parameters: it explains near_x/near_y/radius as 'para una zona puntual' and segundos as the time budget with a default of 25. It also explains tag as filtering by tag signature. However, it does not explain block, layer, limit, or max_depth, which remain undocumented despite 0% coverage, so it is not fully complete.

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 'Extrae atributos de bloque en formato tabla, listo para volcar a planilla' (extracts block attributes in table format, ready to dump to spreadsheet). It mentions specific use cases (carpinterias, locales, plenos, terminaciones, tomas) and distinguishes itself from siblings by noting it enters XREFs and filters by tag signature, which is unique among tools like inspect_block or query_entities.

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 provides conditional guidance: 'Si el computo es de una zona puntual (una unidad, un baño), pasa near_x/near_y/radius' and 'Para un archivo entero subi segundos.' It clearly states when to use the near parameters and how to adjust the time budget, but it does not explicitly mention alternatives or when-not-to-use cases, so it lacks the full 'when/when-not/alternatives' structure.

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