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

Annotations only flag destructiveHint/readOnlyHint; the description goes further by explaining exactly what is destroyed (the whole file is replaced), the refusal condition, the server-side validation and rendering behavior ('checks it against the brief, renders every page'), and the two concrete return states with the editor_url and the polling fallback. That is real behavioral context beyond the structured hints.

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?

Dense but front-loaded: the primary action comes first, then the sibling-routing caveat, then the outcome. The mid-sentence parenthetical interrupts flow slightly, but every sentence carries information the agent needs.

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?

With no output schema, the description carries the return-value burden and does so completely: 'ready' plus editor_url, or 'importing' plus the instruction to poll deck_status. Combined with the destructive scope, refusal condition, and usage split against submit_page, nothing essential 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 75% and 'source' is well documented in the schema itself. The description adds the conceptual framing that source is the complete deck file rather than a page, and indirectly explains wait_seconds ('or importing — then poll deck_status'), but says nothing about label. Baseline 3 is appropriate when the schema carries most of the load.

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 (replace/submit) and resource (the whole deck file) and explicitly scopes it to decks 'whose pages are all written,' which cleanly separates it from submit_page. An agent can pick between the two siblings without opening either schema.

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 an explicit alternative and the condition that selects it: 'while pages are still being written, submit_page each one — a whole file is refused then.' It also routes the follow-up case ('importing' → poll deck_status), so both the when and the what-next are covered.

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