Read posts you have liked

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

Annotations already establish read-only, open-world, and idempotent behavior. The description adds non-obvious behavior: result ordering, own-account-only enforcement, and the platform reason behind that limitation. No contradiction with 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?

Two short sentences, front-loaded with what the tool returns and the key constraint. No filler or repetition of schema defaults.

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 low-complexity read tool with zero required parameters and rich annotations, the description covers purpose, ordering, and a critical account limitation. It lacks explicit pagination/cursor behavior and return shape, but the core call is sufficiently scoped.

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?

The schema already describes limit and account, and the description reinforces the account concept. However, the description adds no information about the undocumented cursor parameter or pagination. At 67% schema coverage, the description should compensate for the cursor gap and does not.

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 clearly identifies the tool as returning posts liked by a connected account, with a specific ordering ('newest first') and a scope limitation (own accounts only). It is distinguishable from list-like siblings because it specifies the liked-posts feed, though it does not explicitly name alternatives such as get_post_likes.

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?

It gives clear context: use for a connected account's liked posts, not for other accounts, because Bluesky does not expose others' likes as a feed. This implicitly tells the agent when not to use it, but it does not name an alternative tool for other like-related queries.

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