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

Adds substantial behavior beyond the annotations: irreversibility of the triggered jobs, that jobs run to completion, that in-flight operations are skipped, that the ordering is dependency-based, and that the call can be a no-op. This is exactly the kind of context annotations cannot 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?

Three tight sentences, no filler. The scope-and-mechanism sentence comes first, then the skip/no-op conditions, then the irreversibility warning last where it lands hardest.

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?

Covers what the tool does, when it does nothing, ordering, and reversibility, with annotations carrying the safety profile. Minor gap: it does not indicate what the caller gets back (e.g., which resources were actually redeployed) and there is no output schema to compensate.

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% and the cluster_id description already points to list_clusters for discovery; the description adds nothing about stack_name format or id resolution. Baseline 3 is appropriate when the schema carries parameter documentation.

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 (redeploy) plus the narrow resource scope (stack resources stuck in creating/updating/stopping) and the mechanism (re-running deployment jobs in dependency order). This clearly separates it from broad siblings like apply_stack_changes, update_stack, or reconcile_cluster.

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 trigger conditions ('resources stuck in a transitional state') and explicit no-op conditions ('call is a no-op when nothing is transitional', in-flight resources skipped). It does not name a named alternative tool for the non-transitional case, which is why it falls short of a 5.

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