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

Annotations already flag a non-read-only, non-idempotent, non-destructive mutation, and the description adds rich context beyond that: nothing is deployed, cross-cluster targets require ai.execute and stacks.write, user confirmation is mandatory, missing/expired slots fail the call, and raw secret-looking values are rejected. The secret-sentinel resolution-at-deploy behavior is exactly the kind of hidden trait this dimension rewards.

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 action and its non-deploying nature are front-loaded, then permissions, secret handling, and follow-up steps follow in a logical order. It is dense and long, but nearly every sentence carries operational information an agent needs, so the length is largely justified.

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?

For a 7-parameter mutation tool with no output schema, the description covers what is created, where it lands, permission and confirmation prerequisites, secret handling, failure modes, and the exact next tools for review and deploy. An agent has everything needed to call it correctly and safely.

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 real meaning: parameters must be supplied as name/value pairs sourced from get_stack_profile, and secret-type parameters must use a ${SECRET_SLOT:<slot-id>} sentinel rather than raw values. The one gap is that it never clarifies the relationship between the required cluster_id and the optional target_cluster_id, which the schema leaves ambiguous.

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 specific verb+resource: 'Create a stack DRAFT from a stack profile,' and immediately delimits scope ('Nothing is deployed: the result is a saved draft'). It clearly separates itself from siblings like create_stack_profile, create_stack_profile_draft, and apply_stack_changes by naming the deploy step as a different tool.

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?

It spells out the when-to-use flows explicitly: current-cluster draft vs the cross-cluster 'move this stack to cluster X' flow, with the alternative create_stack_profile call named as the preceding snapshot step. It also states the required confirmation step, points to list_clusters for candidates, and routes post-instantiation work to load_draft_from_database / apply_stack_changes only on user request.

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