bb_list_directory

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

With no annotations provided, the description carries the full behavioral burden and delivers substantively: it discloses non-recursive scope ('immediate'), the default branch behavior, and the per-item return shape (name, type, path) — genuinely valuable given there is no output schema. It omits pagination and error behavior for nonexistent paths, but the core behavioral traits an agent needs are explicit.

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 sentences with no filler: the first front-loads the action and scope, the second delivers the return item shape — which earns its place precisely because no output schema exists. Every word contributes.

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 read-only listing tool, the description covers the essentials: what is listed (immediate children), where (repo at a ref), and what comes back (name, type, path). Remaining gaps — pagination behavior and error handling for invalid paths — are minor for a first correct call, and the non-obvious root convention is already handled by the schema's path description.

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 exactly 50%: `at` and `path` are well documented in the schema (ref type, empty-string root convention), while `projectKey` and `repoSlug` are bare. The description's prose ('in a repo', 'directory', 'given ref') maps loosely to all four parameters but does not compensate for the undocumented ones, and its ref wording largely echoes the schema. It adds return-shape information, not parameter semantics.

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 and resource: 'List immediate children of a directory in a repo at a given ref'. The phrase 'immediate children' sharply distinguishes it from sibling listing tools (bb_list_branches, bb_list_commits, bb_get_file) and clarifies this is a scoped, non-recursive directory listing. The return item format (name, type FILE/DIRECTORY, path) further disambiguates what a call produces.

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?

Usage context is implied through the ref semantics ('default branch or commit SHA') and the repo/directory framing, so an agent can infer this is for exploring directory structure. However, it never explicitly names alternatives (e.g., bb_get_file for single-file content, bb_search_code for content search) or states when not to use it, leaving sibling differentiation to inference.

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