Posts

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

Annotations only declare openWorld/readOnly/idempotent hints, so the description earns credit for disclosing that the call may consume paid API credits, that confirm=true is mandatory, and that the read-like POST does not publish to social platforms. This explains the otherwise confusing readOnlyHint=false annotation rather than contradicting it.

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-loaded with the core action and return fields, then pagination, then a parameter tip, and finally the credit/confirm caveat. It is dense but every sentence carries information; no padding.

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?

No output schema exists, so the description correctly enumerates returned fields and notes cursor-based pagination. Combined with the confirm/credit caveat, an agent has enough to invoke it correctly; only the sibling relationship is left implicit.

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 100%, so the baseline is 3. The description goes beyond the schema by explaining the performance tradeoff between user_id and handle ('faster response times') and tying confirm to credit consumption, adding meaning the field descriptions alone do not convey.

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?

It states a specific verb and resource ('Fetches a paginated feed of posts from a Bluesky user') and enumerates the returned fields, so the purpose is unmistakable. However, it never distinguishes itself from the adjacent siblings bluesky_post (single post) and bluesky_profile, which an agent must choose among.

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 offers real guidance on parameter choice ('Use user_id (the "did") instead of handle for faster response times') and the confirm=true requirement, which is above the minimum. But it never says when to call this versus bluesky_post or a profile tool, so usage is only implied for a list-vs-single-post decision.

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