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

Annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) are consistent with the text: the description clarifies the crucial behavioral point that "Nothing is removed" while a review is recorded, giving the agent the correct non-destructive mental model. It also discloses the irreversible data implication of the eventual retirement, the absence of an export path, and the required permissions (applications.deploy and stacks.delete) — well beyond what annotations alone convey.

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?

Front-loaded with the purpose and the destructive-warning caveat; every clause carries useful information about returns, safety, and permissions. The middle sentence enumerating what is removed vs. kept is dense but earns its place given the absence of an output schema.

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 carries the return-value burden and does so thoroughly: it itemizes what the retirement removes (stack, namespace, foreign objects, volume claims with reclaim policy) and what it keeps, plus the digest. Combined with the permission requirement and safety warning, an agent has everything needed to call and interpret the tool.

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 100%, so the baseline is 3, but the description adds meaning: it stresses that acknowledge_data_loss must be true and explains the real-world consequence (data is deleted, no export), which reinforces the enum-free boolean constraint. It also frames the digest output the parameters drive, adding context beyond field-level text.

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 and resource ("Prepare the retirement of a managed service") and immediately places it in the workflow as step one of `ankra services delete`. It names the sibling it hands off to (confirm_service_retirement) and the artifact it produces (the digest), so an agent can distinguish it from related lifecycle tools without opening a schema.

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?

Explains the sequencing clearly: this is the preparation step, and confirm_service_retirement consumes the digest it returns. It also states the precondition that acknowledge_data_loss must be true and warns that no export is offered. It stops short of an explicit when-not-to-use statement, so it is strong but not exhaustive.

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