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

Goes well beyond the annotations: it discloses the plan account-cap behavior and the error that points at the billing page, that connected accounts are reported back in-chat in Claude/ChatGPT, and the per-platform connection semantics (Instagram login vs Facebook Pages, LinkedIn profile + company pages, Bluesky handle + app password). Annotations only say non-read-only/non-destructive, so this adds substantial operational context.

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 core action and recipient in the first sentence, then layered with behavior, external_ref, and platform specifics. Dense and mostly waste-free, though the trailing platform-by-platform detail is long enough that it edges toward reference material rather than invocation guidance.

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 and no annotations covering behavior, the description carries the full burden and does: it explains what the caller gets back (in-chat connect button, account reported on connection), the failure mode at the account cap, and platform-specific connection scope. An agent has everything needed to call and interpret it.

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. The description adds cross-tool meaning the schema lacks: external_ref tags connected accounts so list_social_accounts can later be filtered by it, and platform values carry distinct connection behavior (bluesky's app password, linkedin's company pages). expires_in and return_url are left to 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 (get a link), the resource (connect link), and the exact outcome: connecting a new social account to the user's Post Bridge account without dashboard access. It names the nine supported platforms, so an agent can distinguish it from request_upload_link and other siblings without opening 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?

Clear about the operating context: hand the link to the account owner (the user or their client), who approves on the platform's consent screen. It implies the alternative (opening the dashboard) is being avoided, but never explicitly states when not to use this tool or names a competing sibling to route to.

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