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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds non-obvious behavior: alerts fan out to the site plus the named channels, re-watching extends rather than duplicates, and the feature is plan-gated ("Part of Plus"). It stops short of stating auth requirements or any limits on how many watches an account may hold.

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 core action, then the worked trigger example, then the extension rule and delivery note — every sentence carries information. The embedded quoting of a nested JSON literal is slightly hard to parse, but nothing is padding.

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 5-parameter tool with a deeply nested target union, an output schema, and full annotations, the description supplies what structured fields cannot: delivery targets, upsert semantics, plan gating, and a trigger example. The unmentioned portfolio target kind and the absent frequency discussion are the only real omissions.

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 already 80%, so the baseline is 3. The description earns above baseline by giving a concrete triggers payload ("A Tier 1 trader buys" is triggers [{kind:"smart_money", maxTier:1, minUsd:1000, side:"buy"}]) that makes the polymorphic trigger union concrete. It says nothing about the frequency parameter, which the schema covers on its own.

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 opens with a specific verb ("Watch") and enumerates the resources: a Polymarket question, an option, a smart money trader, a forecaster, a category. It also states the effect (Kellian alerts the account that owns this key when it moves), which distinguishes it cleanly from siblings like problee_list_watches and problee_delete_watch. Only gap: the schema's "portfolio" target kind is not mentioned.

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 gives one genuinely useful usage rule — re-watching the same target extends the existing watch rather than creating a duplicate — plus the "Part of Plus" entitlement note. But it never names alternatives or when-not to use it (e.g., how to view watches, how to remove one), leaving routing to inference.

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