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

With no annotations, the description carries the burden, and it does add useful traits: it declares 'Read-only', describes the two return artifacts, and flags the required pre-publication step. However it omits error behavior when the presentation is not yet published as a channel, and gives nothing on auth/scoping or whether the link is stable or expiring.

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?

Three tight fragments front-load the return value, then the prerequisite, then the safety note — no wasted sentences. The telegraphic style ('Direct link (narrator page) and the HTML snippet with the saved look.') is dense but readable, losing only a little clarity for the compression.

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 one-parameter read tool with no output schema, the description covers what comes back and the required setup step, which is the essential information to call it correctly. The main remaining gap is failure behavior if the presentation has not been published as a channel.

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?

The single parameter is fully documented in the schema (agent id UUID sourced from list_agents) at 100% coverage, so the baseline is 3. The description adds no additional meaning about the id — no note on whether it is the agent or presentation id, which is a slight ambiguity given the tool 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?

The description states what the tool returns — a direct narrator-page link plus an HTML snippet rendered with the saved look — which is specific enough to identify the operation. It does not explicitly distinguish itself from the close sibling get_widget_embed_code, so an agent must infer 'presentation' vs 'widget' from the name and the 'narrator page' phrase.

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 gives a concrete prerequisite and ordering rule: publish as a channel first via create_agent_connection with type PRESENTATION_WIDGET. That is real when-to-use guidance naming the exact sibling tool to call beforehand. It stops short of stating exclusions (e.g. when to pick get_widget_embed_code instead) or what happens if the prerequisite is skipped.

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