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

Despite annotations already declaring destructiveHint=true and readOnlyHint=false, the description adds substantial value: PATCH merge semantics, immutable name/type (with failure outcome 'update fails'), cron-field rejection, rollback advice, and explicit out-of-scope list. No contradiction with annotations.

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 most important fact (PATCH semantics) and every subsequent sentence earns its place: immutability, cron rules, rollback, scope exclusions, and learning resources. Dense but not a single wasted word for a 22-parameter tool with this complexity.

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 tool this complex (22 params, 3 required, cron/autoscaling/firewall nuances), the description is remarkably complete for its purpose: it doesn't restate parameters (output schema exists) but instead routes to get_cpln_skill('workload') runbook, get_cpln_rules for defaults, configure_workload_* for advanced sections, and get_resource for rollback safety — exactly the missing context an agent needs.

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% with rich per-parameter descriptions, so baseline is 3. The description adds value above baseline by explaining cross-parameter applicability (autoscaling/timeoutSeconds/debug rejected on cron, schedule rejected on non-cron) and the merge-by-name container strategy that frames how all params behave. Slight deduction because the bulk of per-param meaning still lives in the schema, which is 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?

The description opens with a specific verb+resource ('Update an existing workload') immediately clarifies PATCH semantics (only specified fields change), and distinguishes itself from configure_workload_* and create_workload. The immutability disclosure (type/name require delete+recreate) and cron-specific behavior sharply separate it from siblings.

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?

Explicitly names alternatives: configure_workload_* for advanced spec sections, get_resource(kind='workload') for state capture/rollback, get_cpln_rules for production defaults, and get_cpln_skill('workload') as the runbook. Also gives field-applicability rules for cron vs non-cron. This is exemplary when/when-not guidance.

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