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

Annotations already flag destructiveHint and idempotentHint, but the description goes well beyond them: it enumerates what is destroyed (every frozen membership row for the typed catalog product, up to 20 rows), what is explicitly untouched (wanted-item alerts, price targets, purchase history, seller listings, catalog data), the auth scope required (account:watchlist:write), and fail-closed behavior for stale targets and >20 sibling rows. It is consistent with the annotations rather than contradicting them.

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?

The core intent and precondition are front-loaded, but the text repeats itself noticeably: 'unrelated products and alert preferences remain unchanged/untouched' appears twice, the sibling-row cascade is restated three times, and the account:watchlist:write requirement is given twice in different phrasing. For a three-parameter tool, the ~250-word body carries avoidable duplication.

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?

Given a destructive, idempotent write with an output schema already present, the description covers everything an agent needs: authorization scope, precondition read, cascade scope, refusal limits, atomicity, and the exact recovery sequence. An output schema exists, so the receipt being described in prose is a bonus rather than a gap.

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 100%, so the baseline is 3, and the description earns an increment by adding real meaning: expected_version must come from a fresh supercatch_get_watchlist_target read and be re-read after a version conflict, and the idempotency key must be retained across an uncertain response but replaced for a new intent. Only the listing_id semantics are left entirely to 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 and resource ('Remove the account's membership for the exact listing's typed catalog product at the target snapshot version') and immediately clarifies the non-obvious scope: removal is at the catalog-product level, cascading to all watched sibling listings. This distinguishes it cleanly from supercatch_create_watchlist_item and from listing-level operations in the sibling set.

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?

Gives an explicit gate ('Use only when the account holder explicitly asks to remove this exact listing's watchlist product membership'), a mandatory precondition ('Read the current target snapshot first and pass its exact version'), and a named recovery path (supercatch_list_operations with action account.watchlist.change, then supercatch_get_operation). The 'do not retry with a replacement key' exclusion closes the main failure mode.

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