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

Annotations are uninformative (all false), so the description carries the full burden and delivers richly: per-purpose pricing ($0.05, $0.02/slide, $0.10), 'render NATIVELY on the template (masters/layouts/chrome)', the drop-zone behavior where 'bytes never pass through the agent', and the recreate fallback ('annotate/preserve fallback, refusals free'). This goes far beyond what the schema or annotations 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?

Front-loaded intro sentence, one bullet per purpose, and a single closing paragraph for size and byte-handling notes; every sentence carries distinct information. The minor typos in the recreate bullet ('annotate/preserve fallback, refusals free') are the only blemish on an otherwise tight structure.

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 10-parameter, 8-enum-value tool with no output schema and no informative annotations, the description covers outputs (IDs), costs, constraints, and special behaviors (native template rendering, chained pdf→translate, drop-zone security). The only omission, the 'brand' enum synonym, is already handled in the schema, so nothing an agent needs is missing.

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% and the schema already explains purpose-conditioned parameters (target_language for translate, model overriding quality). The description adds what the schema lacks: max sizes (logo 5MB, image 10MB), costs per purpose, and the omit-data drop-zone behavior. Strong supplement, though the schema still carries substantial per-parameter semantics.

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?

Opens with a specific verb+resource — 'Upload assets for PowerPoint (.pptx) generation' — and then enumerates each purpose with its returned ID and cost (logo→logo_id, theme→theme_id, translate→deck job_id). The detailed purpose list makes the tool's boundary unambiguous against siblings like create_deck, translate_deck, and browse_catalog.

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?

The purpose bullets function as a routing table — 'Use `image` to just place a picture' explicitly steers away from recreate, and the '>3MB' note gives a concrete condition for omitting `data`. However, it never names the translate_deck sibling or states when to prefer upload_asset(translate) over it, leaving one ambiguous branch.

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