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

Annotations already declare destructive=true, non-idempotent, open-world. The description adds a genuinely non-annotated behavioral gate: rollback requires explicit user approval via BEON PASS, which explains the approval_id/beon_* parameters. It still omits what rollback actually does to current traffic/deployments and whether it can be undone.

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?

Two short sentences, front-loaded with the action and followed by the critical constraint. Nothing is wasted, though the second sentence is terse to the point of under-specifying the approval mechanics.

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 destructive, non-idempotent mutation with 8 undocumented parameters and no output schema, the description is too thin: it does not say what state is restored, what happens to the replaced deployment, or how approval is obtained/passed. The approval hint is the only substantive addition.

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 0% across 8 parameters (id, approval_id, beon_* context fields). The description only obliquely connects to the approval parameters via the 'exact user approval in BEON PASS' sentence; it never explains what 'id' refers to or how the beon context fields are supplied. A 2 reflects minimal, indirect compensation for a severe coverage gap.

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 (roll back a deployment) with a scoping qualifier ('previous eligible deployment'). It does not distinguish itself from the other deployment-lifecycle siblings such as railway_restart_deployment, railway_stop_deployment, or railway_cancel_deployment, so an agent must infer the difference.

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?

No statement of when to use rollback versus restart/stop/cancel, no prerequisites beyond 'eligible', and no mention of which deployment version is targeted. The only context given is the approval requirement, which is a precondition rather than usage guidance.

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