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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description does add genuinely useful non-annotation context — credit cost, the warning that repeated requests may purchase data again, and the note that cost varies by operation — but it then contradicts itself by stating both 'at least 10 Nexscope credits' and '1 credit per request', which undermines the very cost guidance it is trying to give.

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?

The core two sentences are well front-loaded, but the remainder is bloated pasted pricing boilerplate that repeats itself ('Use user_id for faster response times' appears twice, along with 'Bluesky Posts API View Pricing', 'Actual supplier units are reported per request', and 'Examples are not guaranteed prices'). This padding dilutes the actionable content and buries the return-field list.

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?

With no output schema, enumerating the return fields (uri, record text, author info, embed, reply/repost/like/quote counts, indexedAt) is valuable and largely completes the picture for a simple read tool. But the phantom cursor reference leaves the pagination story broken, and the contradictory credit figures mean an agent cannot reliably plan or budget the call.

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 description coverage is 100%, so the baseline is 3. The description does add real value by explaining that user_id is the 'did' and yields faster responses, which is a preference rule not encoded in the schema. However, it claims 'Supports pagination via cursor' while the schema exposes only handle and user_id with additionalProperties=false — a cursor parameter that does not exist, which actively misleads about how to page.

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 opening sentence names a specific verb and resource ('Fetches a paginated feed of posts from a Bluesky user') and enumerates the returned fields, so the agent knows exactly what the call produces. It is distinguishable from the single-post sibling social_bluesky_post by the word 'feed', but the description never names that sibling explicitly, keeping it short of a 5.

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?

The only usage guidance is parameter-selection advice: use user_id (the 'did') instead of handle for faster response times. There is no statement of when to choose this tool over social_bluesky_post, social_bluesky_profile, or social_cosmos_user_posts, and no prerequisites are mentioned, so usage is implied rather than directed.

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