Evaluate if data retention has expired by comparing the access time to the maximum retention window. Helps enforce TTL policies.
Check if data retention has expired based on TTL policy.
| Name | Required | Description | Default |
|---|---|---|---|
| accessType | No | ||
| accessedAt | Yes | ISO timestamp of when data was accessed | |
| maxRetentionMs | Yes | Max retention in ms (null = no limit) |
Changes observed during successful MCP inspections.
v5.0.2Input schema / properties / maxRetentionMs / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Input schema / properties / maxRetentionMs / typeAdded value: +[
+ "number",
+ "null"
+]v4.0.0Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / maxRetentionMs / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / maxRetentionMs / typeRemoved value: -[
- "number",
- "null"
-]v2.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only restates the check concept and does not disclose whether maxRetentionMs=null means never expires, how accessType affects the result, or whether the operation is side-effect free.
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 a single sentence with no redundancy, front-loading the verb and subject. It is appropriately terse for what appears to be a simple predicate check.
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 no output schema and no annotations, the description should clarify return semantics and edge cases. It does not state what the tool returns, how null maxRetentionMs behaves, or how accessType is interpreted, leaving an agent without enough information to invoke and use the tool correctly.
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 schema already documents accessedAt and maxRetentionMs, but accessType has only an enum with no explanation and the description adds no meaning. The relationship between accessedAt, maxRetentionMs, and current time is not stated, so the agent cannot infer how the parameters combine to produce a result.
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?
Description states a specific verb ('Check') and resource ('data retention expired based on TTL policy'), which conveys a predicate about retention. It does not explicitly distinguish from sibling 'check_*' tools, but the TTL/retention domain is clear enough to broadly identify the tool's intent.
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?
No guidance is provided on when to use this tool versus alternatives such as check_purpose_permitted, is_evidence_fresh, or compare_timestamps. The description implies a time-based check but gives no context, prerequisites, exclusions, or conditions that would help an agent route to this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.