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

Annotations already carry readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: the response shape (paginited actor profiles with listed fields plus a subject summary), the explicit exclusion (website not on this view), and the pagination caveat ('large social graphs return only the first page; use cursor pagination'). This meaningfully helps the agent call it correctly.

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 that front-load the core purpose before the returns and caveats, with no filler. The pagination caveat and the website exclusion each earn their place, though the sentence carrying response details is slightly dense, packing fields, the summary, and the exclusion into one clause.

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, paginated list tool with a 100%-documented schema, an output schema, and safety annotations, the description is nearly complete: purpose, return fields, pagination behavior, and an exclusion are all present. Rate-limit or error behavior isn't mentioned, but that is a minor gap given the annotations and output schema already supplied.

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 every parameter (actor, limit, cursor, direction) is already documented in the input schema, including the actor handle/DID distinction and the direction enum explanation. The description adds only the return-field context, not parameter details, so baseline 3 is correct — the schema does the heavy lifting.

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 ('Fetch'), a precise resource ('social graph edges for a Bluesky account'), and a clear scope ('who follows them, or who they follow'). It actively distinguishes itself from a sibling by noting 'website is not on this view, only on bsky_get_profile', so an agent can tell it apart from bsky_get_profile without opening either schema.

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 description gives clear functional context for when to call it (fetching followers/following) and an explicit redirection: if website data is needed, use bsky_get_profile. The schema further routes bare-name lookups to bsky_search_actors. It lacks a broader when-to-use vs. not statement, but the sibling differentiation is concrete and useful.

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