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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is known. The description adds genuinely new behavioral context: the destructive action is confined to a draft and sends nothing to the chat counterpart, which reassures the agent about blast radius. It says nothing about what happens to an already-sent draft or whether a discard is reversible.

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?

Two short sentences, zero filler, with the identity of the action and its non-sending nature front-loaded before the usage restriction. Every clause earns its place.

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 three-parameter mutation fully described by schema and annotations, the description covers the two things structured data cannot convey: what the tool acts on and that no message is transmitted. No output schema is needed for a discard confirmation, and nothing an agent needs to invoke it correctly is missing.

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 100%, so log_id provenance from list_message_drafts, brand_id selection, and the operation_id retry semantics are all already documented in the schema. The description adds no parameter meaning beyond that, which is the baseline case.

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 ('Descarta') plus the exact resource ('un borrador de list_message_drafts') and immediately delimits the scope ('sin enviarlo: no manda nada a la persona del chat'), which is precisely what separates it from send_message_draft in the sibling list.

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 an explicit gating condition for use ('Úsala solo cuando el usuario lo pidió'), which is meaningful guidance for a destructive tool. It does not name send_message_draft as the contrasting action or state when-not beyond the user-intent rule, so it stops short of full routing guidance.

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