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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The phrase 'privacy-filtered' adds one useful behavioral trait not in annotations – results are filtered by privacy scope – which explains why output may be incomplete. But it doesn't say whether errors occur on unauthorized projects, or pagination behavior.

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 tight sentence with no filler, and the filtering concept is front-loaded. It's short enough that it leaves room to say more, but nothing is wasted.

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 5 params (4 of which have misleading schema text), no output schema, and no annotation on return shape, the description should explain what the listing returns and how the optional IDs act as filters. It does neither, so an agent can't form a full call plan.

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 nominally 100%, so the baseline is 3, but the schema descriptions for requestId, sessionId, executionId, and presentationId are copy-paste copies of the projectId description ('Owned project ID returned by list_linked_projects'), which is actively misleading – those parameters are not project IDs. The description adds nothing to clarify what these IDs mean or which are optional filters.

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 says 'Read hosted list presentations' – a verb and resource – but 'hosted list presentations' is an odd compound that doesn't clearly distinguish from siblings like get_presentation or presentation_read. 'Privacy-filtered project metadata' hints at scope but the exact listing behavior (which presentations, for whom) is vague.

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?

No when-to-use guidance, no alternates named, no exclusion of get_presentation/presentation_read despite those siblings existing. The agent must infer that this is the bulk-list operation versus the single-item get.

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