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

Beyond annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses meaningful behavior: secrets are never returned by CONFIG, wait defaults to true and polls until deployed with component URLs, wait=false is a trigger-only mode, and progress is emitted to stderr or MCP logging. It stops short of stating timeouts/permission requirements tied to maxWaitMinutes or what happens if polling exceeds the wait budget.

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 description is dense and front-loaded: the resource identity comes first, then one clause per action, then the delete pointer and the logging note. Each sentence covers a distinct topic, though the heavy parenthetical nesting makes it read more like a compressed spec than clean prose.

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 an 8-parameter, non-idempotent, open-world mutation tool with no output schema and only 25% schema coverage, the description covers the action model and wait behavior adequately but leaves the polling-tuning parameters and branchName semantics undocumented. An agent could call it, but would have to guess at the limits of the polling controls.

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 only 25%, so the description carries a real burden and does partially meet it: it explains the `wait` default and trade-off and ties bnsEnvironmentId to STATUS polling. However, `branchName`, `maxWaitMinutes`, and `pollIntervalSeconds` are left to bare schema names, leaving over half the parameters without semantic explanation.

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 names the resource (BunnyShell / Environment-as-a-Service lifecycle) and enumerates three concrete actions with what each returns or produces (CONFIG settings, PROVISION environment, STATUS poll). It explicitly distinguishes the delete path by naming destroy-ephemeral-environment, though it does not differentiate itself from read-side siblings like get-eaas-config or list-bunnyshell-environment-events.

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 gives clear per-action guidance: use CONFIG for settings, PROVISION to create (with a wait default and a wait=false escape hatch), STATUS to poll bnsEnvironmentId, and destroy-ephemeral-environment to delete. That routes the agent well among the lifecycle verbs, but there is no explicit statement of when not to use this tool versus the adjacent config/event-read tools.

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