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

The read-only annotation is already declared via readOnlyHint=true, and the description repeats it ('Read-only'), adding no new safety information. It does add useful behavioral context: results are per-resource and ordered newest first, and the data is scoped to a cluster. It says nothing about pagination behavior beyond the max_versions cap or retention/limits of history.

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 tight sentences: the first front-loads what is returned and its ordering, the second gives the use cases. No filler sentences and every clause carries information.

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, the description usefully characterizes the return content (who/what/when, per resource, newest first), which is exactly what an agent needs to interpret results. Given the readOnlyHint annotation and full schema coverage, remaining gaps (pagination semantics, history depth) are minor.

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 description coverage is 100%, so cluster_id, stack_name, max_versions and resource_type are already fully documented. The description hints at the resource_type filter ('per resource') and ordering ('newest first') but adds no syntax or format detail beyond the schema, making the baseline 3 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?

States a specific verb+resource (get a stack's version history) and enriches it with scope: 'who changed what and when, per resource, newest first.' An agent immediately knows this is a change-audit read. It does not name sibling history tools (e.g. get_stack_deployments, resource_timeline), so it stops short of full sibling differentiation.

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?

Gives explicit when-to-use conditions: answer 'what changed in this stack' and find the version to roll back to. That ties the tool to concrete intents. However, it names no alternatives or exclusions, so the agent must still infer that this is preferred over other stack-history surfaces.

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