File info

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the permission requirement and the shape of the result, but says nothing about failure modes (e.g. whether a nonexistent path errors or simply reports exists=false) or whether it follows symlinks – gaps that matter for a stat operation.

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 clauses, front-loaded with the action and its outputs, with no filler. It is terse rather than verbose, which is appropriate but leaves no room for the missing usage detail.

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 one-parameter read-only tool with no output schema, disclosing the returned fields inline is a reasonable substitute. Still, no error semantics and no path-format guidance leave it only minimally complete for an agent deciding between it and bb_read_file/bb_list_dir.

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 0%: the single "path" parameter has no description in the schema. The description only says "a path," without clarifying whether it expects an absolute path, a path relative to the project root, or a file vs directory, and the sibling tools mix project-scoped and filesystem concepts, so this ambiguity is real.

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?

"Stat a path" gives a specific verb and resource, and the enumeration of returns (exists, type, size, modified time) marks it clearly as metadata-only, distinguishing it in practice from bb_read_file and bb_list_dir. It never names those siblings explicitly, so the differentiation is inferential rather than stated.

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?

The description supplies one useful precondition ("Needs file-system permission"), which tells the agent this may fail without a grant, but it gives no when-to-use guidance relative to bb_read_file, bb_list_dir, or bb_request_fs. Usage is implied by the verb "stat" rather than explained.

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