mdl_watchlist_add

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

Annotations already declare a non-read-only, non-idempotent, open-world mutation. The description adds real value beyond them: it states the host-configured auth requirement, warns that it changes data on MyDramaList, and flags that no typed request model or numeric status mapping exists ('do not invent a status code'). It does not contradict the annotations.

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?

Front-loads the action ('Watchlist: add') and each following sentence contributes a distinct constraint (field scope, param nature, auth, mutation caution). Some sentences are terse fragments, but nothing 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?

For a mutation tool with no output schema and an untyped parameter, the description covers auth, mutation semantics, the opaque param shape, and a caution against inventing status codes. It omits what the response looks like and whether the operation merges or replaces an existing entry, but is otherwise solid.

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% on a single opaque nested object, so the description must carry the burden. It explains that item is the 'upstream sync JSON object' and that no typed request model exists, which helps, but it never enumerates the accepted fields (episode progress, rating, dates, notes are only named loosely). Partial compensation only.

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 ('Add or update a watchlist entry') and enumerates the fields involved (episode progress, rating, dates, notes). It is clearly distinguishable from the sibling mdl_watchlist_remove and the fetch variants, though it does not explicitly name any sibling.

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 when-to-use constraint ('use only for an explicit user request') and notes the authentication prerequisite. It does not name alternatives like mdl_watchlist_remove or the fetch tools, but the context provided is clear and actionable.

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