Read posts you have liked

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

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), so the description's added value is the ordering guarantee and the hard scoping limitation tied to a platform constraint. It adds real context beyond the structured fields, though pagination behavior via cursor is left unaddressed.

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 sentences with zero filler, front-loading what the tool returns before the constraint that limits it. Every clause earns its place.

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 read-only listing tool with no output schema, the description covers scope, ordering, and the main failure condition. The unmentioned cursor/pagination semantics are a minor gap that the caller can infer from the schema.

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 67%: limit and account are described in the schema, cursor is not. The description adds no parameter-level detail at all, so it neither compensates for the undocumented cursor nor enriches the documented ones. Baseline 3 is appropriate given the schema does most of the work.

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 ('Posts a connected account has liked') plus ordering ('newest first'), so an agent knows exactly what it retrieves. It does not name a sibling, but the scoping rule implicitly separates it from tools like get_post_likes that read likes on a given post.

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 a clear applicability rule: only for your own accounts, with the reason ('Bluesky does not expose anyone else's likes as a feed'). That tells the agent when the call will fail, though it never names an alternative tool for other sources.

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