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

Annotations already declare mutation (readOnlyHint=false), idempotency, and non-destructiveness; the description adds context the annotations cannot: the plan-level 25-ticker ceiling, the ~30-minute alert latency after an SEC filing, downstream effects (leading the daily email briefing), and that calls never consume the daily quota. It does not flag how the replace action overwrites the existing list, which is the one genuinely risky behavior left undisclosed.

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?

Identity and plan cap are front-loaded, then benefits, then example phrasings, so the agent gets the essentials immediately. Some promotional phrasing ('INSTANT EMAIL ALERTS', 'lead the daily email briefing') is slightly padded, though it does convey real downstream behavior.

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 an output schema present the return shape needn't be explained, and annotations plus full schema coverage handle safety and parameters. Against that, the description supplies the plan limit, alert timing, and quota exemption. The remaining gap is replace semantics and error behavior when the 25-ticker cap is exceeded.

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% and both parameters, including the action enum with per-value meanings, are fully documented in the schema, so the baseline is 3. The description adds the practical constraint of a 25-ticker Edge-plan cap, which is real value, but it does not clarify ticker resolution behavior (symbol vs. name) or what 'replace' does to existing entries.

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 names the resource precisely (the user's CapitalSnitch watchlist) and the effects of membership (instant alerts, daily briefing inclusion), and the sample utterances implicitly enumerate the operations list/add/remove. It stops short of explicitly contrasting itself with adjacent siblings like get_my_alerts or set_alert_preferences, so an agent must infer that this tool owns membership rather than alert delivery settings.

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?

Four concrete user utterances cover the main invocation contexts (alert me on insiders, add tickers, what am I watching, stop alerting), which maps cleanly onto list/add/remove. There is no explicit 'do not use this for X, use Y instead' routing, and the boundary with set_alert_preferences (tuning what kinds of alerts fire) is left implicit.

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