read_conversation

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

Annotations already declare readOnly/openWorld/destructive=false, but the description adds real behavioral context: Deleted Items exclusion, cursor stability rules, per-body paging, best-effort coverage with shared scan budgets, and the untrusted-data warning. The only unaddressed point is why idempotentHint is false, which the cursor semantics imply but never state.

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?

Purpose is front-loaded in the first sentence and the remaining sentences are terse and information-dense, each covering a distinct behavior. It is jargon-heavy but almost no sentence 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?

An output schema exists, so return-value explanation is not required, and pagination/coverage caveats are well covered. The gap is the two required identifiers, whose meaning and provenance an agent must know to call this correctly at 0% schema coverage.

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% and there are 5 parameters, so the description carries the full burden. It only gestures at 'cursor'/'next_cursor' and 'limit' and vaguely at body paging; the two required parameters entry_id and store_id are never explained, and body_limit is not defined. The compensating detail is partial at best.

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 gives a specific verb and resource ('Read the native conversation across accessible stores/folders') and adds scoping detail (ConversationIndex order, Deleted Items excluded). It does not explicitly name why an agent would pick this over search_emails or read_email, though it notes read_email continues body paging.

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?

There is operational guidance for continuing a page ('Follow next_cursor with unchanged arguments except limit') and a pointer that 'read_email continues' body paging, which implies usage. However, it never states when to use this tool versus the sibling search_emails or read_email, so the routing decision is only implied.

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