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

Annotations already cover read-only, open-world and idempotent behavior, and the description adds genuinely new traits: no credentials required, results come back in provider order with generator AT-URIs and creator identities, and the upstream method app.bsky.unspecced.getPopularFeedGenerators is unstable and may change or disappear. That last point is exactly the kind of risk an agent can't get from structured fields.

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?

Four tight sentences, front-loaded with the core action and scope, then exclusions, then return shape and next step, then risk and pagination. No sentence is filler; each adds an operational fact.

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 three-parameter, open-world search tool with an output schema, everything an agent needs is present: scope boundaries, auth posture, result ordering, upstream instability, and how to continue paging. Return-value detail is appropriately left to the output 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 100%, and the description adds real meaning on top: query targets catalog metadata rather than post text, and cursor is opaque and must be replayed with the identical query. It does not restate the limit clamping rule, but the schema already documents that, so the marginal gain is solid rather than exceptional.

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 and resource ("Search metadata in the provider's public feed catalog") and immediately delimits scope by saying it searches feed names and descriptions, not post text. It also names the downstream sibling (bsky_get_feed) for reading posts, so an agent can place it precisely among the feed-related siblings.

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?

Explicitly sets expectations about exhaustiveness ("does not enumerate every feed") and routes the agent to bsky_get_feed with a feedUri once a feed is found. Pagination guidance ("Continue with the returned opaque cursor and the same query") gives the agent the exact loop to follow.

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