Add an entity to a watchlist that is RE-SCREENED daily. You get alerted (webhook/email) the first time it appears on any federal exclusion or sanctions list. Use for continuous vendor / counterparty monitoring.
| Name | Required | Description | Default |
|---|---|---|---|
| npi | No | ||
| name | Yes | ||
| No | Optional email alerted on a new hit. | ||
| webhook | No | Optional URL POSTed on a new hit. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses daily rescreening, alert on first hit via webhook/email. However, it does not cover whether the tool is idempotent, what happens on subsequent hits, how to remove entities, or any permission/auth requirements.
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?
Two sentences, front-loaded with the core action. Every clause adds value. No redundant or vague language.
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?
Moderate complexity (4 params, no output schema, no nested objects). The description covers the purpose and alert mechanism but omits lifecycle details (e.g., how to stop monitoring, what happens after a hit, idempotency) that would help an agent fully grasp the tool's behavior.
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 50% (only email and webhook have descriptions). The description adds no meaning to the required 'name' or optional 'npi' parameters beyond their names. It implies email and webhook are for alerts, but does not compensate for undocumented parameters.
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?
Clearly states the action: 'Add an entity to a watchlist that is RE-SCREENED daily.' Specifies the resource (entity to a watchlist) and the use case (continuous vendor/counterparty monitoring). Distinguishes from sibling tools by emphasizing ongoing monitoring vs. batch or one-time screening.
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?
Explicitly states when to use: 'Use for continuous vendor / counterparty monitoring.' Provides clear context but does not explicitly mention when not to use or suggest alternatives among the listed siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct use case: full roster rescreen with compliance receipt, bulk screening up to 50 entities, single entity check, and continuous daily monitoring. No overlap in purpose.
Three tools follow verb_noun pattern (screen_batch, screen_exclusion, watch_entity), but roster_rescreen reverses the order (noun_verb). Still, all use snake_case and are readable.
Four tools are appropriate for the domain of exclusion screening, covering single, batch, roster-wide, and ongoing monitoring without unnecessary bloat.
Covers all primary workflows—one-off, batch, full roster, and continuous watch. Minor gap: no tool to remove entities from watchlist, but this can be handled externally.