watchlist_reorder

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is known; the description nevertheless adds real value by disclosing the mechanism (verified clear-and-append), the side effect ('temporarily empties the list'), and the guarantee that list identity is preserved. It stops short of saying whether a failure mid-append leaves the list empty, which is the crucial remaining behavior for a destructive tool.

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, no filler, with the core operation and its invariant front-loaded before the caveat about the implementation. Slightly jargony ('verified clear-and-append', 'no guessed reorder endpoint') but every clause carries information.

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?

Seven parameters, a destructive mutation, and no output schema make the description the main narrative channel, and it covers the mechanism and the temporary-empty risk. It omits failure/rollback behavior and any hint that a browser tab target and layout guard are prerequisites, which the schema supplies but the prose never ties together.

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 71%, so the schema carries most parameter meaning and a 3 baseline applies. The description's 'exactly the same symbols and section headers' reinforces the entries contract (including section headers) but says nothing about target_id, idempotency_key, expected_layout_id, or expected_entries_sha256, so it does not compensate for the uncovered remainder.

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 (reorder) and resource (symbols and section headers within a watchlist), plus the invariant that the ID/name are preserved. It does not name or contrast with watchlist_set_entries or watchlist_reconcile, so the agent must infer the boundary itself from 'exactly the same symbols'.

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?

'Reorder exactly the same symbols and section headers' implies the precondition that the entry set must be unchanged, which is useful when-to-use context. But there is no explicit when-not, no named alternative for adding/removing entries, and no statement of what the caller should do if the set differs.

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