List Bluesky direct-message conversations

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

Annotations already cover read-only and non-destructive hints. The description adds valuable behavioral detail: the need for a privileged app password, that errors for a chat-capable password are a password property not a connection issue, and that unknown filter values are refused by name rather than silently dropped. This goes beyond the annotations without contradicting them.

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 description is substantial but every sentence earns its place: purpose, return details, cost, password nuance, and filters. It's front-loaded with the primary function and then layers prerequisites and edge cases. It could be slightly tighter, but the complexity justifies the length and it remains scannable.

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?

Given there is no output schema, the description adequately covers what the tool returns (conversation participants, unread counts, request status) and explains the key prerequisite (privileged app password). It also addresses filter behavior and error semantics. Combined with the annotations, an agent has enough to call it correctly without missing critical details.

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?

With 80% schema description coverage, the schema documents most parameters. The description augments this by explaining the meaning of 'request' (someone not followed), the purpose of filters (readState, status, kind), and the error handling for unknown filter values. It adds context to the enum parameters that plain enum values wouldn't convey.

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 description states a specific verb (reads) and resource (DM conversations) with the exact data returned: who each is with, unread count, and request status. It immediately distinguishes itself from siblings on other platforms (list_x_dms, list_meta_conversations) by naming Bluesky and the AT Protocol.

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?

It clearly explains when to use the tool (to read DM conversations) and provides prerequisites (privileged app password), which is essential context. It does not explicitly say 'use this instead of X', but the platform-specific focus and filter descriptions remove ambiguity. It also states it's free and requires no vendor approval, which helps an agent decide.

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