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

With no annotations, the description carries the full burden and does disclose key traits: it is asynchronous, fast ('a few seconds'), and preserves content while swapping visual treatments. It never says whether the original deck is overwritten or a new version is produced, nor whether logo/brand changes require ownership of the deck — important for a mutation tool.

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?

One sentence establishes the operation, its inputs, and the content-preserving guarantee, and the second sentence delivers the only required follow-up action. Nothing is redundant and the most decision-relevant facts come first.

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 an async mutation with no output schema, the description covers the essential gap — that results are retrieved via get_presentation rather than returned. It leaves open whether the source deck is replaced and what happens to the job if it fails, which keeps it just short of complete.

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 78% and six of the nine parameters already carry descriptions (including that image style re-picks images). The description lists the same knobs without adding format, defaults, or precedence rules, and says nothing about job_id, brand_name's length limit, logo_base64, or how remove_brand interacts with brand_name.

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 — 'Re-render a finished deck' — and enumerates the swap dimensions (theme, font, icon pack, animation level, image style, brand). 'Finished deck' plus the job_id requirement cleanly separates it from create_presentation, which builds a new 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?

Makes the post-call workflow explicit by naming the sibling to poll ('Poll get_presentation afterwards for the new links'), which is the main usage ambiguity for an async job. It doesn't state when to prefer restyle over creating a fresh deck or what to do on failure, 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.