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

The description frames the tool as a plain read, yet the annotations declare readOnlyHint=false and destructiveHint=true; an agent relying on the text would not expect any irreversible or mutating behavior, and nothing in the description warns about what could be destroyed. It also says nothing about the session/bootstrap handshake implied by read_skills and expected_catalog_version, which is exactly the kind of behavior the description should surface beyond the flags.

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 single sentence is front-loaded and free of padding, so there is no waste to trim. The problem is under-specification rather than verbosity — brevity here costs information rather than buying clarity.

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 for a tool with six parameters, nested objects, a required skill-proof array, and a catalog-version handshake, one sentence is far from sufficient. It never clarifies which documents/folders are in scope, what the GenAds linkage is, or how the call must be prepared.

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 six parameters and only 50% schema description coverage, the description needs to compensate, but it explains none of them. The opaque "arguments" object with additionalProperties=false, plus work_id and request_key, are undocumented in both schema and description, leaving an agent to guess how to form a valid call.

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 sentence pairs a specific verb ("Read") with a concrete resource ("saved document metadata and folders"), so the basic operation is understandable. However, it merely restates the title verbatim and never mentions the GenAds/ad-document scope implied by the tool name, nor distinguishes itself from near-siblings such as list_studio_documents, native.read_document, or read_studio_document.

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?

There is no when-to-use guidance, no prerequisites, and no named alternative among the many document-listing/reading siblings. The description gives no signal for choosing this over list_studio_documents or native.read_document, so an agent must infer the choice from the tool name alone.

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