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

Annotations declare destructive=true, idempotent=true and openWorld=true, but the description adds behavior they cannot express: publishing is asynchronous, the PUBLISHING state means the send is still in flight, and the agent must consult get_post to confirm status and resulting link per destination before claiming success. This is exactly the extra context a mutating, multi-destination publish tool needs.

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 the action and the scheduling branch, then the usage gate, then the verification caveat. Sentences are dense but each carries a distinct constraint. The interaction etiquette clause (ask only for missing data, respect confirmations) is slightly peripheral but still actionable.

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 shapes need not be described, and annotations cover the safety profile. The description supplies the missing pieces: prerequisite draft, now-vs-scheduled branching, and post-publish verification. It leaves open what happens on partial failure across destinations or whether an already-published carousel can be re-published.

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?

There is only one parameter, post_id, and the schema has zero description coverage, though it does constrain the value to a UUID pattern. The description compensates partially by tying the identifier to a draft produced by create_carousel_draft, implying post_id is that draft's ID. It never states this explicitly, so meaning beyond the schema is only inferred.

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 and resource ('publica un carrusel guardado'), names the tool that produces the input (create_carousel_draft), and scopes publishing to all connected networks simultaneously or as a scheduled post when a date exists. An agent can distinguish this from create_carousel_draft (drafting) and create_and_publish_carousel (combined create+release) 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?

Gives an explicit gate: use only when the user asked to publish or schedule, and requires the draft to already exist via create_carousel_draft. It even refines the interaction pattern (only ask for missing brand/networks/timing data, respect client confirmations). It stops short of naming sibling alternatives such as publish_post, publish_now, or create_and_publish_carousel, which would make routing fully unambiguous.

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