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

The description frames the tool as a pure "Read" of a saved export, yet the annotations declare readOnlyHint=false and destructiveHint=true. That is a direct conflict over whether this call is a safe read or a mutating/destructive operation, and the description offers no hint of what side effect occurs (e.g. whether minting the private download invalidates or consumes the saved export). No permission, scope, or side-effect disclosure compensates for this.

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?

Three short sentences, front-loaded with the purpose before the state caveat and the expired-link escape hatch. Every sentence carries information; only minor tightening would improve it.

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 values need not be explained, but a six-parameter, nested-object, open-world tool whose annotations flag it as destructive needs more than a one-line read framing. The description neither resolves the read/destructive tension nor explains the required invocation envelope (request_key, expected_catalog_version semantics are left entirely to the schema).

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?

Six parameters at 50% schema coverage: the schema documents read_skills, publication_proposal_id, and expected_catalog_version, but the description says nothing about work_id, arguments.run_id, or request_key, which are the required ones an agent must actually supply. Given the low coverage, the description was expected to compensate and does not.

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?

"Read this project's saved pack export and private download" names a specific verb (read) and a specific resource (the saved pack export plus its private download artifact), and the state qualifier "when complete" narrows it further. It is distinguishable from the sibling writers native.genads_export_pack and native.genads_stop_pack_export by implication of state-reading, but those siblings are never named, so the differentiation is indirect rather than explicit.

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?

"Queued is not complete" is a genuine pre-condition that tells the agent not to call this while the export is still queued, and "An expired link can be renewed for free in the project's Creative packs controls" tells the agent where to go when the link is dead rather than re-calling this tool. What is missing is an explicit named alternative (e.g. poll with get_run_status vs. call this) for the incomplete case, so the routing is only partial.

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