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

Annotations already declare destructiveness, open-world access, and non-idempotency, so the bar is lower. The description does add real behavioral context beyond them — that a provider metadata inspection must be authorized, that request_id must be stable, that the description field must avoid secrets, and that no provider write/backup occurs. It still omits the effect of a revision mismatch and what a checkpoint actually captures.

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?

It is only three sentences and front-loads the save action, but the opening clause ('after authorized provider metadata inspection') is jargon-heavy and vague, and the parameter guidance is wedged into the middle rather than structured as an ordered list.

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 10 parameters, no output schema, and 0% schema coverage, the description is too thin. It does not explain conflict behavior, what the checkpoint stores, or how the many fields relate, leaving an agent likely to misuse it.

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 10 parameters, so the description carries the full burden, yet it only touches expected_revision, expected_head_id ('branch head, null initially'), and request_id. Required fields such as app_id, environment, commit_sha, and description's semantics, plus optional branch/task_refs/release_id, are left entirely to the bare schema.

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 states a specific verb+resource ('Save a named checkpoint of an exact source commit'), which is clearly distinguishable from siblings like beon_pin_app_checkpoint or beon_prepare_app_checkpoint_restore. However, it never explicitly contrasts itself against those nearby tools, so an agent must infer the distinction.

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 implies a precondition ('after authorized provider metadata inspection') and a boundary ('No backup purchased or provider write'), which hints at when it applies. But there is no explicit when-to-use/when-not guidance relative to the many checkpoint/prepare siblings, leaving usage largely inferred.

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