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

With no annotations, the description carries the full behavioral burden and does so thoroughly: alert eligibility rules, no historical replay, what the `data` field contains including stripped internal `_` fields, cursor-based pagination, and even webhook signature verification/replay-protection requirements. It does not contradict anything and discloses traits (dedup behavior, detection-window semantics) that no schema could 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-loads the core purpose and kind definitions before the mechanics, and every sentence is information-dense rather than padded. The webhook signature/2xx-5s paragraph is arguably tangential to invoking get_alerts and slightly inflates the block, keeping this from a 5.

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, so the description must explain what comes back — it does, via the `data` field explanation and the `next_cursor` pagination note. Combined with the alert-eligibility rules, sizing limits, and filtering semantics, an agent has everything needed to call this correctly without additional context.

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 baseline is 3, but the description adds real meaning beyond the terse schema strings — it expands each `kind` enum value into a concrete definition (disclosed this week, new 5%+ activist stake, awards at/above your threshold, newly modified) and clarifies that alert `data` is the stored source record. It does not add syntax detail for `since` or `limit` beyond the schema.

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 resource and scope: 'Your watchlist alerts, newest first,' scoped to the API key making the call. It enumerates the three alert kinds with the exact conditions that produce each, which clearly separates it from raw-data siblings like get_congressional_trades, get_federal_contracts, and get_activist_stakes.

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?

Gives clear conditions for when an event becomes an alert (7-day window, not before the entry was added, dedup on award modifications) and states the watchlist is managed on keyvex.com, not via this tool. It also hints at alternatives by noting 'the matching tool may present the same record differently,' but never names a sibling tool or says explicitly when to prefer raw endpoints over alerts.

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