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

Annotations declare write, non-idempotent, open-world behavior, and the description adds substantial context beyond that: SocialClaw never sees the password, most providers return an authorizeUrl, and Telegram/Discord require pre-created tokens/webhooks. This is rich behavioral disclosure that the structured fields do not provide.

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-loaded with the action, then the provider branching, then the safety note. Three sentences, each earning its place, though slightly long. No filler.

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?

Covers the full connect workflow including provider-specific parameter requirements and safety guidance. No output schema exists, but the return of authorizeUrl is mentioned, making it complete for an agent to act.

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%, so the baseline is 3, but the description explains provider-specific parameter usage (which parameters apply to Telegram vs Discord) and stresses only passing user-provided values, adding meaning beyond the schema.

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+resource (connect a social account) and scopes it to the user's own accounts and their SocialClaw workspace. It is clearly distinguishable from siblings like list_accounts or delete_instagram_comment.

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 clear usage context: the user signs in with the provider, and Telegram/Discord special cases are explained. It doesn't explicitly name an alternative tool, but the flow (start connecting, then hand URL to user) makes when-to-use clear.

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