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

Adds substantial context beyond annotations: the link expires in one hour, nothing is connected until the user completes the flow, the page signs in on the network's own site, and Instagram requires a Business/Creator account. Annotations already cover mutation/safety hints, so the description's job is mostly the lifecycle and flow, which it handles well — though it doesn't say whether regenerating a link invalidates the previous one.

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 fact (one-hour link, browser flow) in the first sentence, then layers scope, Instagram specifics, and the client-link contrast. Dense but each clause carries information; the Instagram detail is slightly long for a general-purpose tool.

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?

No output schema exists, and the description compensates by describing the return values (url of the page, message_for_user: one plain sentence telling the person what to do). Combined with expiry, flow behavior, and parameter effects, 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 baseline is 3, but the description adds real meaning: 'With platform the page offers only that network; with brand_id the accounts are connected to that brand.' That explains the consequence of each parameter, which the schema labels alone do not.

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 — creates a one-hour link the user opens to connect social accounts — and names the networks involved. Clearly distinguished from sibling link tools by describing what the link ultimately does (browser flow to connect accounts to PostWire).

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 routes between alternatives: 'The link works for one hour and is for the person in the chat; a client connecting their own accounts gets a client link instead: a private page for their brand that works for 30 days.' That names both the condition and the sibling tool (create_client_link) to use instead.

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