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

Goes well beyond the annotations: discloses pricing ($0.01 per successful call), the x402/USDC-on-Base payment flow including the _meta["x402/payment"] key, that failed/no-match calls are uncharged, and that results are ordered newest-first with next_cursor for paging. For a paid, open-world search endpoint those are the behaviors an agent most needs before invoking 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 search capability and scope in the first sentence, then the return fields, then cost mechanics. The field enumeration is a long run-on ('text, author handle and display name, likes, replies, reposts, language, media links, time and URL'), but it earns its space given there is no output schema.

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, the description compensates by enumerating the returned fields and the pagination token, and it covers the payment requirement an agent must satisfy to succeed. Nothing material about calling this endpoint correctly is missing.

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 schema already explains q (search syntax), limit (1-25, default 25) and cursor. The description only adds that next_cursor from the response feeds the cursor parameter, otherwise restating the schema — baseline 3 is correct.

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 concrete verb and resource — 'find public Bluesky posts by keyword, phrase, hashtag or from:handle' — plus the transport (AT Protocol AppView) and ordering (newest first). The keyword-search framing implicitly separates it from the sibling bluesky_posts, though it never names that sibling as the non-search alternative.

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?

'Social listening on Bluesky for brands, products and topics' gives a clear usage context, and the note that bad input / no-match calls are free tells the agent when a call is cheap to attempt. It stops short of explicit when-not-to-use guidance or naming a competing tool such as bluesky_posts or social_search.

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