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

Annotations only declare readOnly/openWorld, but the description adds substantial behavior beyond them: paging semantics with offset/limit, a 1000-entry and ~1 MB per-page bound, the truncated:true signal, total/next_offset fields, and the fact that every response including errors carries a pauhu-library-receipt/2 receivable by library_verify. That is exactly the extra context annotations cannot provide.

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?

Front-loaded with the core capability and information-dense with no filler, but the single long paragraph with stacked parentheticals is harder to parse than it needs to be for pagination and receipt details.

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 and no required parameters, the description takes on the burden and does it: it explains the per-file return shape, pagination fields and bound conditions, and the receipt envelope including error responses. An agent has enough to call and interpret it.

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 already 86%, but the description adds meaning: ref is resolved to a commit sha before the read, version is checked against the registry's sha512 tarball integrity, and repo/package are mutually exclusive. It competes with a strong schema rather than duplicating it, though per-parameter detail is mostly left to the schema.

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 and resource: listing files under a path of a public GitHub repo at a commit sha, or an npm package at a verified version. It also names what the listing returns (type, size, git blob id), which cleanly separates it from code_read and code_grep without opening their schemas.

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?

Clear context for when this is the right tool: directory-level enumeration of a repo/package pinned to an exact identity, with the repo/package mutual exclusivity spelled out in the parameters. It never names a sibling as an alternative (e.g. code_read for a single file), so there is no explicit when-not guidance.

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