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

Annotations already cover the safety profile, and the description adds substantial context on top: a fixed return shape with `truncated`/`totalCount`, the differing entry path formats between modes, and the explicit rule that a nonexistent ref raises an error rather than returning an empty listing. That error-vs-empty distinction is exactly the kind of behavioral detail an agent needs and cannot get from the schema.

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 tight sentences, each carrying new information, with the core behavior front-loaded ahead of return-shape and edge-case details. Minor friction from compressed phrasing such as "at a ref" and the capitalized "BOTH modes", which reads tersely but still parses.

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 takes on the return-value burden and discharges it well by naming every field. It stops short of explaining how to resume from a truncated result (e.g., paging with `path`), which is the one operational gap for a tool whose complexity is otherwise fully covered.

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 only 40% – only `ref` and `path` are documented there, while `repo`, `owner`, and `recursive` are bare. The description compensates by explaining that `path` scopes to a subtree in both modes and that `recursive: true` walks the whole subtree, which is the key interaction an agent must get right; `owner`/`repo` are self-evident and their absence is forgivable.

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+resource ("List directory contents at a ref") scoped to a repo tree, which is clearly distinct from siblings like merjax_read_file or merjax_search_code by implication. It never names a sibling or explicitly contrasts with them, so an agent must infer the boundary itself.

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 is implied rather than stated: the recursive vs non-recursive distinction and the fact that `path` works in both modes tell the agent how to shape a call. There is no explicit guidance on when to choose this tool over file-reading or code-search siblings, and no exclusions.

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