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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description usefully adds the sign-in/auth requirement and clarifies that 'watching/reading' maps to the 'current' shelf, plus that progress is optional. It still doesn't state what happens when the title already exists (whether it overwrites progress or shelf) or what is returned, which are meaningful gaps for an idempotency-sensitive mutation.

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?

A single dense sentence with the mutation front-loaded ahead of the status mapping and the auth prerequisite. The parenthetical enum list is long but each element is load-bearing; only the semicolon splice makes it slightly harder to scan than it needs to be.

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 4-parameter mutation with no output schema and thin annotations, the description covers the essentials an agent needs: the action, the shelf vocabulary, optionality of progress, and the auth gate. It could reasonably add what to do when the title name is ambiguous or missing (the schema hints at slugs from search results, implying resolve_title) but the core is complete.

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 75% and the schema already documents title, progress and media_type. The description adds real semantic value the schema does not: the human-facing shelf vocabulary ('watching/reading') mapped onto the 'current' enum value, and confirmation that progress is optional. It adds nothing for media_type, but the status mapping alone exceeds the baseline.

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?

The description states a specific verb+resource ('Add a title to the signed-in person's AnimeHunt library') and additionally covers the move-between-shelves case, which is a distinct operation an agent would otherwise miss. It is clear and unambiguous, but never names or contrasts against sibling tools like my_library (read side) or rate_title, so it stops short of full sibling differentiation.

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?

Usage is implied rather than stated: it makes clear this is the write path for library membership and shelf changes, and that sign-in is a prerequisite. However, it gives no when-not-to-use guidance and never points to alternatives (e.g. my_library to read the library, rate_title to score a title), leaving routing decisions to inference.

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