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

The readOnlyHint=true annotation already establishes this is a safe read, so the bar is lower, and the description adds a genuine precondition the annotations do not cover: the deck must already be rendered for this to work. It also discloses the return shape and ordering ('images, page 1 first'). It does not discuss pagination limits or how many pages return at once, a minor gap.

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 sentence that leads with what is returned, then folds in inspection criteria, the remediation path, and the availability precondition. Every clause earns its place; the only cost is that the run-on construction makes it slightly harder to scan.

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 two-parameter read tool with no output schema, the description covers the return medium and ordering, the precondition for calling it, and the downstream workflow. The only missing piece is any explicit note on deck_id versus guest_token selection, which would round it out.

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 description coverage is 50%: guest_token is documented in the schema (only for account-less decks), but deck_id carries no description anywhere. The description adds no parameter meaning at all, though deck_id is largely self-evident from its name, so this lands at the baseline rather than below it.

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?

The description names a specific resource and scope: 'The deck's rendered pages as images, page 1 first.' An agent immediately knows this returns per-page renderings rather than status or metadata. It stops short of explicitly differentiating itself from siblings like deck_status or submit_page, so it is clear but not sibling-routing.

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?

It states exactly when to reach for this tool ('available once the deck has been rendered'), what to inspect the output for ('overlapping or clipped text, odd spacing, an element off its page, a picture that does not say its page's claim'), and what to do next ('fix that page and submit_page it again'), naming the follow-up sibling. That is explicit when/when-next/alternative guidance.

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