Estado del enriquecimiento masivo

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

Annotations already cover read-only and open-world safety, so the description earns credit for adding what annotations cannot: it never returns the lead list, exposes the phase lifecycle, and discloses that phone resolution can take roughly an hour. It does not explain whether the call blocks or how wait_seconds changes the blocking behavior, which is the one behavioral trait left undisclosed.

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 scoping constraint is front-loaded in the first clause, followed by the phase vocabulary and then actionable guidance; every sentence carries information. Line breaks fragment the text slightly but nothing is redundant.

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?

An output schema exists, so return-shape explanation is rightly omitted, and the lifecycle/latency context is well covered. However, for a polling tool whose entire risk is over-waiting, leaving wait_seconds semantics undocumented is a real gap in what an agent needs to call it 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?

Schema description coverage is 0% for two parameters, so the description must carry the load — but it says nothing about task_id or wait_seconds (default 30). An agent cannot tell from any source whether wait_seconds makes the call long-poll for up to N seconds, which directly interacts with the advice not to wait in a loop. The only mention of 'partial=true' refers to a parameter of get_bulk_results, not of this tool.

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 exactly what is returned (progress counters of a bulk job) and explicitly rules out the adjacent resource ('nunca la lista'), which is the main ambiguity versus the sibling get_bulk_results. The enumerated phase values make the resource concrete enough for an agent to recognize it without opening the 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?

Gives explicit routing: read decided leads via get_bulk_results when partial=true, and for phase=awaiting_phones it prescribes a concrete action (notify the user and re-poll later) with an explicit prohibition on waiting in a loop. This is when/when-not guidance with a named alternative, not just implied usage.

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