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

Goes well beyond the annotations: no credits, nothing deleted, history preserved, instant propagation to share links, compare reversal semantics, the confirmation prompt when recipients have already opened the document, and the full publisher-permission model (owner, admins, up to 5 listed people, everyone-mode). The only nuance is that destructiveHint=true sits slightly at odds with its 'nothing is deleted' framing, but that hint is defensible for a change to what viewers see and is not a contradiction.

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 action in the first sentence, and nearly every clause carries information an agent needs. It is a single long run-on paragraph with policy, error codes and permission rules interleaved, which costs some scannability but is justified by the tool's complexity.

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?

For a 7-parameter, high-stakes mutation with no output schema, the description covers what is created, what is preserved, permissions, plan gating, refusal codes, confirmation behavior and the returned fields (new version number, restored version, fileName, staleDrafts). Nothing essential for correct invocation 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 would be 3, and the description earns an upgrade by supplying the critical 'exactly one of version and fileName' invariant that the schema cannot express (no parameters are marked required). It also explains that confirm/confirmationToken answer a prior preview, though it does not spell out docId/shareId interplay beyond the schema text.

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?

Specific verb and resource: 'Makes an earlier version of a document the current one again', immediately clarifying that a new version is created from a stored file rather than an upload or AI regeneration. This cleanly separates it from siblings like lnkdrp_remove_latest_version, lnkdrp_replace_pdf and lnkdrp_publish_draft.

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?

Explicit routing rules: version vs fileName ('exactly one of the two'), a pointer to lnkdrp_list_revisions to discover version numbers and names, the Free-plan fallback to lnkdrp_stage_pdf, and the full list of refusal codes. An agent knows when to pick this tool and what to do when it fails.

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