watchlist_set_entries

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

Beyond the destructiveHint, it discloses that the list is temporarily emptied during the operation and that durable checkpoints plus exact read-back expose partial failure — meaningful hazard and failure-mode context. It still omits recovery guidance (e.g., whether retrying with the idempotency key rolls back) and auth/permission requirements.

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?

Two sentences, front-loaded with the replace purpose and hazard, with no filler. 'using known remove then append endpoints' is slightly implementation-flavored jargon but still earns its place by explaining why the list empties.

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 destructive, 7-parameter tool with no output schema it covers the essential hazard and partial-failure detection. It leaves notable gaps around atomicity, rollback/retry semantics, and how the mandatory idempotency key and layout guard interact with a mid-operation failure.

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 description adds no parameter-level meaning at all; schema coverage is only 71% and timeout_ms is undocumented, so the description does not compensate for the gap. The heavy lifting on entries, target_id, watchlist_id, idempotency_key, and expected_layout_id is entirely in the schema.

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+resource ('Replace watchlist content/order') that is clearly distinct from add/remove/reorder siblings. It does not explicitly name an alternative tool, so sibling differentiation is implied by the replace semantics rather than described.

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?

'Replace' implies the when (full-set overwrite) but the description never states when to prefer this over watchlist_add, watchlist_add_bulk, watchlist_import, or watchlist_reconcile. The 'temporarily empties the list' line is a caution, not an explicit usage rule.

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