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

Annotations already mark the tool read-only and non-destructive, and the description adds useful traits: the response shape is invariant, recursive entries use full repo-relative paths while non-recursive entries use bare names, and a nonexistent ref is an error, never an empty listing. This goes well beyond the annotations and helps agents interpret results and errors.

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?

Four dense sentences, with the opener immediately stating the operation. Every sentence adds either mode semantics, return shape, or error behavior, with no filler or repetition of schema content.

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 no output schema, the description explicitly supplies the return shape and path-format differences, which is the key missing information. It also states the error contract for bad refs. It does not exhaustively define `truncated`/`totalCount`, but their names and the fixed shape are enough for a listing tool of this complexity.

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 only 40%, but the description compensates for the two non-trivial parameters: it explains that `path` scopes the listing in both modes and that `recursive: true` selects subtree-walking. `owner`/`repo`/`ref` are either standard repository identifiers or already documented in the schema ('Branch / tag / sha'), so the gap is not harmful.

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 opens with a specific verb and resource: 'List directory contents at a ref.' It clarifies that `path` scopes a subtree and distinguishes the two modes, so the tool is clearly a directory-listing utility rather than a file-content/read tool. This differentiates it from sibling tools like read_file and repo_read_file without ambiguity.

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 gives concrete context for when options matter: `path` scopes the listing in both modes, and `recursive: true` switches from one level to the whole subtree. It does not explicitly name alternatives or say when not to use the tool, but the behavioral guidance is sufficient to select modes correctly. There is no exclusionary guidance, so a 4 rather than 5.

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