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

The description goes beyond annotations by explaining the trigger condition (percentile_below OR delta_below with an example), the evaluation cadence (after daily baseline refresh), delivery channels (webhook/email), and scope (per API key). Annotations only state non-read-only, non-idempotent, non-destructive, so the description carries a substantial burden and does so with actionable detail, though it does not address overwrite behavior or response format, which is partially covered by the output schema.

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?

The description is moderately long but each sentence serves a purpose: it front-loads the core action and shifts the context to 'stop polling and be notified,' then details conditions, cadence, delivery, and scope. It is slightly verbose with phrases like 'Phase 5' and 'wake me when it matters' that add flavor but not critical data, yet it remains structured and readable.

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?

Given the tool's complexity (4 params, one required, an output schema, and non-trivial trigger logic), the description covers what an agent needs: the action, the condition formula, the delivery methods, and the evaluation timing. It doesn't explain the response structure because the output schema exists, and it omits overwrite semantics but that is a minor gap for a tool whose primary function is setting an alert. Overall it is complete enough for correct invocation.

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?

Since schema coverage is 100%, the baseline is 3, but the description adds valuable meaning by explaining the relationship between percentile_below and delta_below, giving a concrete example (-8) for delta_below, and clarifying that notify is a delivery configuration. It effectively teaches the agent how the two threshold parameters combine, which the schema alone does not convey.

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 clearly states the action (set a drift alert), the target (a saved shortlist), and the purpose (notify when a site's national standing moves materially). It distinguishes from siblings like set_market_alert and set_site_alert by explicitly scoping to shortlists, and even frames it as a 'wake me when it matters' loop, so an agent immediately knows what resource and condition this applies to.

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 ('stop polling and be notified') and for what scenario ('long-running siting campaigns'), giving clear context for invocation. It doesn't explicitly name alternatives or when not to use it, but the shortlist scope and the existence of sibling tools for market/site alerts make the exclusion implicit, which is adequate.

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