link

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

No annotations are provided, so the description carries the full behavioral burden. It shows an 'op' parameter (add/update/remove) per action but never states that these operations mutate the document, whether removal is reversible, what permissions or document state are needed, or what 'list' returns. For a mutation-capable tool this is a significant disclosure gap.

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?

A single dense line that front-loads the resource list and then the per-action signatures. Nothing is padded, and the action:signature format is scannable. It leans on terse abbreviations (op?, url?) but stays compact.

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 an 11-parameter, four-action tool with no annotations, no output schema, and only 36% schema coverage, the action-to-parameter mapping is the most valuable thing the description could provide and it does provide it. It remains incomplete on handle usage, mutation/return behavior, and parameter meaning, so it is adequate rather than thorough.

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 description coverage is only 36% across 11 parameters, so the description must compensate. It does add genuine value by mapping which parameters belong to which action (e.g. cross_ref takes at, show, target, bookmark, hyperlink), which the flat schema cannot express. However, it omits 'handle' entirely and gives no meaning for url, name, or op beyond their names.

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 names the three resources it governs (hyperlink, bookmark, cross-reference) and enumerates four concrete actions, so an agent knows this is the link/bookmark/cross-ref manipulation tool. It is clear and specific, though it never explicitly contrasts itself with unrelated siblings like field or toc (which could plausibly overlap with cross-references).

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?

The action list implies what each subcommand does structurally, but there is no guidance on when to choose hyperlink vs cross_ref vs bookmark, no prerequisites, and no mention that a document handle from an open document is required. The agent must infer selection entirely from the parameter signatures.

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