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

Adds real context beyond the annotations: what is preserved ("the rest of the deck is untouched"), the quota model ("each slide has one free redo"), the refusal failure mode, and the return shape ("the whole deck, in order, ... attached"). It is consistent with destructiveHint=false and idempotentHint=false; only latency/cost of a redraw is left unstated.

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-loads what the tool does, then the inspection requirement, the limits, and the return shape. Dense but nearly every clause carries operational information; the closing return-shape sentence is slightly redundant with the opening 'swap them into the same deck'.

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?

No output schema exists, and the description compensates by stating the return (whole deck in order, redone slides in place, attached). Preconditions, per-call limits, free-redo policy and the refusal fallback cover everything needed to invoke it correctly.

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 adds genuine meaning: slides are 1-based, capped at 1-4 per call, and `note` should describe the defect with a concrete example ("the second bullet is misspelt"). `job_id` provenance (from create_visual) is also clarified beyond the schema's "The carousel job id".

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?

Names a specific verb and resource ("Redraw chosen slides of a FINISHED carousel") and anchors it to the sibling that creates the deck ("its job_id from create_visual"). It also implicitly separates itself from animate_carousel, redo_animated_slides and create_visual by restricting scope to text/quality fixes on an existing deck.

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?

Explicit preconditions and exclusions: "LOOK at the slides first (get_job attaches them) and redo only the ones that are wrong", a hard cap of "1-4 slides per call", and a fallback ("a slide already redone is refused — make the deck again with create_visual instead"). An agent knows exactly when to call this and what to do when it fails.

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