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

Annotations already disclose openWorldHint=true and readOnlyHint=false, but the description adds critical non-obvious behavior: the tool does not itself connect the channel; it returns a link that a human must open. It also notes Bluesky credential requirements and the required follow-up call. No contradiction with annotations.

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-loads the core behavior ('Returns a link a PERSON must open') and then adds only necessary operational context. Every sentence carries unique information: human-in-the-loop constraint, credential requirement, follow-up action, and profile limit. No wasted words.

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 adequately explains that the return value is a link and what the agent must do with it. It covers the human-interaction model, platform-specific credential needs, follow-up verification, and an edge case, leaving no critical gap for an agent to invoke it correctly.

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 75%, with handle, appPassword, and connectionType already described in the schema. The description reinforces Bluesky's handle/appPassword need and mentions Instagram's limit, but adds no parameter-level detail beyond what the schema already states. Baseline 3 is appropriate.

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: returns a link a person must open to connect a network. Clearly distinguishes this from sibling list_channels by framing this as the initiation step, with list_channels as the follow-up verification. An agent can tell this is not a direct connection tool.

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 says when to use it (to get a connection link for a person) and when not to attempt it alone ('You cannot complete this yourself: every network asks a human to sign in'). It also names the follow-up action (call list_channels with refresh) and handles the Instagram one-per-profile edge case.

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