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

Annotations only supply safety hints (readOnlyHint=false, openWorldHint=true, destructiveHint=false); the description adds substantial behavioral context beyond them: that the agent cannot complete the action itself, that the client link only permits connecting, expires in 7 days, and can be revoked in Accounts or via revoke_connect_link.

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 purpose in the first sentence, then details the for_client variant. The second sentence is dense with parentheticals but each clause carries distinct information without redundancy.

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 6 parameters, 0 required, and no output schema, the description covers what the tool returns (a link), who uses it (a human, or an agency's client), and its constraints. It is largely complete, though it does not specify a default when neither platform nor reconnectAccountId is provided.

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 adds meaning beyond the schema by explaining the intent of for_client (a link to forward to the client) and the alternate selection mode between reconnectAccountId and platform. It reinforces and contextualizes the parameters rather than merely restating them.

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 ('Return a link... to connect a new social account, or to reconnect one whose token expired'), covering both the new-connect and reconnect flows. An agent can distinguish this from siblings like list_connect_links and revoke_connect_link 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?

Explicitly explains the human-in-the-loop condition ('An agent cannot complete this itself... handing over the link is what unblocks the person') and names the alternative path: for_client: true when the accounts belong to an agency's client. Both the when and the when-to-use-variant are stated.

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