Search posts

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond them: the connected-account requirement and the fact that the public unauthenticated API rejects this endpoint. It stops short of describing result ordering or paging behavior.

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?

Three sentences, purpose and scope front-loaded, then capability and prerequisite. The operator list is long but each item is directly usable; no filler text.

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?

The tool has no output schema and eight parameters, yet the description says nothing about what a result contains (author, text, engagement) or default sort/paging behavior. Auth prerequisites and query syntax are well covered, but the return shape is left for the agent to discover.

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 88% (baseline 3), but the description goes further by enumerating the operator syntax accepted in q (from:, to:, mentions:, domain:, since:, until:, lang:, quoted phrases), which is more actionable than the schema's brief 'Operators like from:... work inside it'. Undocumented cursor is not addressed.

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 with scope: 'Full-text search across public posts.' This cleanly separates it from siblings like search_actors, search_feeds, and get_author_feed without needing to open any 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?

Gives a clear precondition ('Requires a connected account') and a notable constraint ('Bluesky's public API refuses this endpoint'), so the agent knows auth is mandatory. It does not, however, name alternatives (e.g., search_actors for users, get_author_feed for one author's posts) or state when-not to use it.

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