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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description goes far beyond by disclosing the TTL reaper, namespace isolation, that it cannot affect existing deployments, the ingress-rendering conditions, and the exact return shape (preview_url, components[], top-level image/service = entry component only). This is exactly the behavioral context annotations cannot carry.

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 core action and scope are front-loaded in the first sentence, and nearly every clause carries distinct information. It is dense and parenthetical-heavy for a single block, which slightly taxes readability, but nothing is filler.

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 complex, non-idempotent mutation with 7 parameters, a nested object, and no output schema, the description covers prerequisites, isolation/safety, environment-variable and database semantics, and the full return contract. An agent has everything needed to invoke it correctly.

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% and the schema descriptions are already thorough, but the description adds real meaning: env values merge over saved demo defaults and 'these win by name', sentinels are resolved server-side and mounted via a Kubernetes Secret, and entry_component drives root-path ownership while siblings keep path prefixes. It largely reinforces rather than contradicts the schema, so it lands above the baseline 3.

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 (deploy a throwaway, time-limited demo of an Application's PR build) and pins down scope precisely: an isolated ankra-demo-pr-<n> namespace on the staging cluster. This is clearly distinguishable from siblings like deploy_application, redeploy_demo, and demo_stop.

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 clear preconditions (requires a configured staging cluster, application_id, pr_number, image_tag) and states it is 'safe in ask mode' because the demo is isolated and reaped at TTL. It does not, however, name an alternative sibling or an explicit when-not-to-use condition (e.g., redeploy_demo vs deploy_pr_demo), so it stops short of full routing guidance.

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