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

readOnlyHint=true already declares the safe, non-mutating profile, and the description usefully confirms 'Does not publish' and adds that the call also surfaces current recipient membership — a behavioral disclosure beyond the annotation. It still does not describe failure modes (e.g., what happens for items outside the chat) or any limits on the preview.

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 short, front-loaded sentences: action first, then the non-publishing guarantee, then the selection constraint. No filler and nothing buried.

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 return-value duty and does indicate one key return element (current recipient membership), but it does not describe what the previewed message copy looks like or how errors surface. For a 3-required-parameter read-only tool this is close to adequate, with a small gap on output expectations.

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 0%, so the description must carry the parameter burden and only partially does: 'explicitly selected direct-chat messages' maps to item_ids and 'shared project' to project_id, and the warning against unrelated history constrains item selection. It adds no information about chat_id's role or the item_ids max/min bounds that the schema enforces.

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 (preview) plus the exact resource and scope: explicitly selected direct-chat messages being copied to a shared project, and it also reports current recipient membership. The phrase 'Does not publish' implicitly contrasts it with the sibling share_direct_chat_items, so an agent can distinguish the dry-run from the real share 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?

'Does not publish' gives a clear context cue that this is the pre-flight/validation step rather than the committing action, and 'Never select unrelated chat history' constrains how to choose items. It stops short of explicitly naming share_direct_chat_items as the follow-up alternative or stating exclusions, so it is clear but not fully routing.

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