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

Despite no annotations, the description discloses the core behavior: it 'windows two CMS reassignment snapshots' and 'returns net churn per org + the dropped NPIs.' It also specifies the data source ('CMS public-domain records') and pricing. This goes beyond a simple read hint by explaining the comparative methodology. It does not describe pagination or rate limits, but for a search tool this is acceptable and nothing contradicts annotations (which are absent).

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 front-loaded with a compelling question and flows logically: question, methodology, filters, output, data source, price. It is relatively compact for the amount of context it provides. One minor distraction is the jargon-y phrase 'the facility-losing-clinicians backfill tell,' which may confuse some users, but overall the structure is effective and every sentence adds value.

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?

The description covers the essential 'what', 'how', and 'what you get' for this tool: it explains the snapshot comparison, lists filters, defines the output as 'net churn per org + the dropped NPIs,' and notes the public-domain source. Since the tool has no output schema, the description gives enough high-level return information. It does not specify exact output fields or pagination behavior, but for a read-only search tool with well-described parameters, it is reasonably complete.

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?

The input schema already provides detailed descriptions and examples for all 8 parameters (100% coverage), including the semantics of 'since' as 'Baseline snapshot: latest vs earliest on/after this date.' The description's mention of filters like 'state, specialty, org, group_id, min_dropped, or a since baseline' simply summarizes the parameters without adding new meaning beyond the schema. Baseline of 3 is appropriate.

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 precise question, 'Which medical groups are losing clinicians?', then explains the mechanism: comparing two CMS reassignment snapshots by individual→group affiliation to find clinicians present in the prior snapshot but gone in the latest. This clearly identifies both the resource (medical groups / clinicians) and the specific analysis (exodus). Although it doesn't explicitly name sibling tools, the distinctive focus on provider exodus separates it from similar search tools like pecos_enrollments_search.

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?

The description states the context for use: finding groups losing clinicians and identifying 'the facility-losing-clinicians backfill tell.' It also enumerates filters ('Filter by state, specialty, org (group name), group_id, min_dropped, or a since baseline'), indicating when and how to narrow the search. However, it does not explicitly mention alternatives or when not to use this tool, so it misses the 'when-not' guidance for a 5.

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