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

Annotations only declare readOnly/idempotent/destructive hints; the description adds substantial context beyond them: argv runs without a shell, no secrets or env vars reach the workspace, the call blocks up to timeout_seconds (max 330), one concurrent call per repository and a few per organisation, what workspace_unavailable means, that passed is true only for exit 0, and that stdout/stderr tails are untrusted data. It also names the required workspaces.use permission.

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?

Purpose and the key constraint (warm pod on Ankra's compute, not your machine) are front-loaded, and nearly every sentence carries a distinct operational fact. The block is long and slightly dense, but very little of it is disposable.

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 still explains the return shape (exit code, passed flag, stdout_tail/stderr_tail), the failure mode (workspace_unavailable with its causes), permission requirements, concurrency and timeout limits, and input size limits. Nothing material an agent needs to invoke it correctly is missing.

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 100%, so baseline is 3, but the description adds real meaning: files are written over the checkout and restored afterwards, command plus files are capped at 64 KB, timeout is capped at 330 seconds, and branch runs on its head (commit_sha overrides). This goes beyond the schema's own parameter docs.

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?

States a specific verb (run a command), the resource (Ankra Workspace warm pod with the repository's toolchain), the scope (head of a branch, optionally with files written over the checkout), and the return (exit code plus output tail). An agent can distinguish this from file-reading siblings like workspace_read_file without opening either schema.

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?

Explicitly says to use it for heavy commands (build, test, lint, typecheck) instead of running them locally, and that uncommitted changes should be passed as files — a clear when-to-use with an implicit alternative ruled out. It does not, however, contrast itself against the sibling workspace_* tools, so routing between those still requires inference.

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