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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the tool returns URLs and no account mutation occurs server-side, preventing an agent from assuming it can complete a connection. It doesn't say whether URLs are single-use, expire, or require an existing session.

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?

Two short sentences, both earning their place, with the key constraint ('never through this server') front-loaded in the second sentence. The parenthetical platform list is dense but functional, mapping the scope of returned URLs.

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 one required parameter, no nested objects, and no output schema, the description should explain the return shape (a list of URLs, a map keyed by platform, or a single tracking URL) and it doesn't. The platform enumeration hints at the shape but leaves the agent unsure what key or field to read.

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 description coverage is 100%, so productId is documented as 'The product id.' The description adds nothing about what productId scopes: whether URLs differ per product or whether an unknown id errors. Baseline 3 applies where the schema carries the parameter burden.

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?

The description states a specific resource: the browser URLs used to connect social/ad/email accounts and tracking. It also makes the tool's real function explicit (handing back URLs rather than performing a connection), which the bare name 'connect' would otherwise obscure. It stops short of a crisp verb-form statement such as 'Returns the URLs for…'.

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?

Usage is implied rather than stated: 'Account connections happen in the browser, never through this server' tells an agent what not to expect, which is useful. However, it never says when to call this tool (e.g. when a user asks to link an account or when auth is missing) and names no alternative among siblings like actions, run, or plan.

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