processDefinition_setHistoryTtlByKey

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

The description discloses critical behavioral scope ('for all versions') and the unit of measurement ('days'). However, with no annotations provided, it should further clarify the mutation's safety profile—such as whether the change is immediate, reversible, or affects existing historic data versus only new data.

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 appropriately concise with two efficient sentences. It is front-loaded with the primary action and scope, though the second sentence ('Controls historic data retention') is slightly generic.

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 empty input schema (which ideally should contain the key and TTL parameters), the description should clarify how inputs are provided. It adequately covers the operation's intent but leaves ambiguity around the mechanism given the schema/implementation gap.

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?

With zero parameters, the baseline score is 4. The description adds semantic value by specifying the unit as 'days', which explains the expected temporal input format even though the schema itself is empty.

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 ('Update'), resource ('history time-to-live'), unit ('in days'), and scope ('for all versions of a process definition by key'). The explicit 'by key' phrasing effectively distinguishes this from the sibling tool processDefinition_setHistoryTtlById.

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?

While 'by key' implies the identifier type, the description lacks explicit guidance on when to use this tool versus the 'ById' variant or other history management tools. No prerequisites or exclusion criteria are mentioned.

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