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

Annotations cover the safety profile (readOnly=false, destructive=true, idempotent=true), and the description adds substantial context beyond them: browser-login auth rather than an API key, a per-account cap with a named error code, and the fact that the write is immediate while list_my_followed_bills reads a lagging replica. That last point prevents an agent from wrongly concluding the follow failed.

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 mutation plus auth caveat, then usage, then failure mode, then read-after-write caveat — a sensible ordering with no filler sentences. The dashboard clause in the second sentence is mildly redundant with the list_my_followed_bills reference but earns its place as disambiguation.

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?

For a two-parameter mutation with an output schema, everything an agent needs is present: auth model, default behavior, cap and error semantics, and staleness of subsequent reads. No gaps remain that would cause a misinvocation.

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 real meaning by contrasting notify=true (notifications on) with notify=false ("follows it quietly"), which is a consequence the schema's terse one-liner does not convey. bill_id is left entirely to the schema, which already says it comes from list_bills.

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 (adds a bill to this user's watchlist) and explicitly ties it to the sibling list_my_followed_bills as the same list, with the dashboard as an external referent. An agent can separate it from list_my_followed_bills and unfollow_bill without opening a 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?

"Use it when someone asks to follow, track or watch a bill" gives the triggering intent in the user's own vocabulary, and the notify default/override is spelled out. It also gives the failure path (cap → FOLLOW_LIMIT_REACHED, retrying will not help, must unfollow first), which implicitly routes to unfollow_bill.

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