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

Annotations only declare the mutation/idempotency/safety flags; the description adds genuinely new behavioral facts: it is a two-party flow that cannot be completed by the agent alone, it returns a `launch_url`, verification fails with a clear message until the role exists, and no ARN or secret must be transcribed. This is exactly the kind of context annotations cannot convey.

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 and the blocker, then the verbatim hand-off steps, then the next call — a logical order an agent can follow directly. It is longer than most definitions, and a couple of clauses (the 'no ARN or secret needs to be copied' reassurance) could be folded, but nearly every sentence carries operational value.

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 still names the key return value (`launch_url`) and the subsequent `connection_id`. For a non-idempotent, human-gated mutation it covers preconditions, side effects, expected failure mode, and next step — nothing an agent needs in order to call it correctly is missing.

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 0%, so the description carries the full burden and largely does: `provider` is fixed to "aws" today, `account_id` is specified as a 12-digit AWS number, and `software` is explained along with its omission default (Cloud Cost Sentinel) and the one-link-per-software rule. Only `label` and `region` go unexplained, which is a minor residual gap rather than a substantive one; this sits between 4 and 5 and earns the higher end given how much undocumented schema it compensates for.

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 first sentence states a concrete verb and resource ('Start linking a cloud account so it can be scanned'), and the description explicitly routes to the sibling `verify_connection` for the follow-up step. An agent can distinguish this from `get_connection`/`list_connections`/`verify_connection` without inspecting 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?

It states when to use it, the preconditions (human with AWS credentials must be present), the required hand-off script, and the exact next tool to call (`verify_connection`) with its connection_id. It also pre-empts a likely mistake by saying polling every ~15s is safe and expected.

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