layerfs_fs_stat

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description adds only the word "saved," which is too vague to convey what state is being inspected or what happens when the path or ref does not exist.

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?

A single front-loaded sentence with no filler, but the brevity here reflects under-specification rather than disciplined editing — there is nothing after the core claim to build on.

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?

With two required, undocumented parameters, no output schema, and a 0% schema coverage rate, the description would need to explain the ref/path pair and what metadata is returned. It does neither, leaving the agent guessing before invocation.

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%, so the description carries the full burden and does not meet it: "ref" is entirely unexplained (branch? commit? snapshot?) and "path" is only weakly implied by "file or directory." Neither required parameter's expected format or relationship is clarified.

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 verb+resource pair ("Read" + "file or directory metadata") is identifiable and separates it from content reads like layerfs_fs_read and listings like layerfs_fs_list. However, "saved" is ambiguous — it could mean persisted commits, snapshots, or working-tree state — and no sibling is named to anchor 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?

There is no guidance on when to choose stat over layerfs_fs_read, layerfs_fs_list, or layerfs_operator_files_stats / layerfs_operator_store_stats, which all sound adjacent. The agent must infer the selection rule.

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