Mark watched or unwatched

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

Annotations already declare readOnlyHint=false and idempotentHint=false; the description goes beyond them by explaining why writes are non-idempotent ("marking watched also records a play") and by disclosing partial-failure semantics ("the error names the keys already marked"), which is genuinely useful for retry decisions. The gap is the unwatched path: it doesn't say whether removing watched status deletes existing play history.

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?

Four short sentences, front-loaded with the action and scope, then progressively finer constraints and failure behavior. No filler.

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 two-parameter mutation with no output schema, the description covers the side effect and partial-failure reporting, which are the things an agent most needs. It stops short of stating what the successful response contains (counts vs per-key status) and of describing the unwatched side effect.

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 0%, so the description carries the burden; it does clarify that ratingKeys must be explicit owner-account keys rather than titles or filters. It adds nothing about the numeric string format or the 1-100 item cap, and nothing about the boolean's edge behavior (e.g. marking an already-watched item).

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?

A specific verb pair (mark watched/unwatched) plus the resource (items addressed by ratingKey), with the account scope called out as owner. It is clearly distinct from siblings like watch_history (read) or rate_item, though it never names those siblings explicitly.

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?

"Explicit keys only" tells the agent it must already hold ratingKeys (e.g. from search/get_item) rather than addressing items by filter, which is useful implied guidance. However, it never states when to prefer this over rate_item, watch_history, or manage_watchlist, nor any exclusions or prerequisites.

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