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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: large payloads come back as complete base64 byte chunks resumed via sha256+offset, and metadata changes force a restart of the pagination—exactly the kind of operational constraint an agent cannot infer from structured fields.

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?

Three sentences with no filler and the core action front-loaded, but the chunking sentence is telegraphic and grammatically broken ('Large JSON is complete base64 byte chunks'), which forces re-reading and blunts the otherwise efficient structure.

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 an output schema present, return shape needn't be restated, and the description covers the two things that matter for correct invocation: accepted identifier forms and the continuation/restart protocol. It stops short of stating chunk size limits, what a partial response looks like, or error behavior, which would be needed for full completeness on a paginated read.

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 50% and the nested continuation object has no property descriptions at all, so the description must compensate—and it does, explaining that bundleId accepts an id, a personal slug, a live URL or a page URL, and that continuation is a cursor carrying a chunk hash plus an offset. Minor flaw: it says 'nextOffset' while the schema property is named 'offset', a naming mismatch that could confuse an implementer.

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?

Opens with a specific verb+resource: 'Read full bundle metadata and manifest', which clearly separates it from bundle_list (enumeration) and bundle_get_file (file payload). It does not explicitly name those siblings, but the 'full metadata and manifest' framing makes the scope distinguishable.

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 through the continuation instructions ('pass chunk.sha256 and nextOffset in continuation') and the restart caveat, which effectively tell the agent this is a potentially multi-call read. However there is no explicit when-to-use/when-not guidance and no routing to bundle_list or bundle_get_file for the alternative cases.

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