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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds real substance beyond them: the set replaces live screenshots in EVERY language, null restores the live set, captions bind to the new set when present and otherwise to that language's live screenshots, and the call returns the listing overview with problems. These are non-obvious side effects and return semantics that the structured fields do not convey.

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?

A single dense, front-loaded paragraph that leads with the action and scope before drilling into parameters. Every sentence carries information, though the caption-set interaction is embedded mid-paragraph where a short break would scan better.

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 nested-object mutation with no output schema, the description covers the draft-vs-live distinction, ordering and count constraints, the null revert path, caption binding rules, character limits, and the return value. An agent has everything needed to invoke it correctly without further exploration.

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 coverage is 100%, so the baseline is 3, but the description earns above baseline by explaining the draft/replace semantics of screenshots, the meaning of null, and the non-obvious interaction where captions apply to the live screenshots of a language when no new set is passed. It duplicates some constraints (order, 200 chars, limits) that the schema already encodes.

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 ("Changes the listing's screenshots") plus a scope qualifier ("in the draft") that separates this from live-listing mutations. It explicitly names the sibling that produces the input ids (upload_screenshot) and the sibling that reads back state (get_listing), so an agent can place it in the workflow without opening schemas.

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 clear usage context: ids come from upload_screenshot, order matters, max 10, and passing null reverts to live screenshots. It explains the two operating modes but never states when NOT to use it or how it relates to the sibling pick_screenshots, so it stops short of full when/when-not guidance.

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