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

Annotations only declare readOnlyHint=false, so the description carries most of the burden and does well: it discloses replace semantics ("Replaces the definition"), file retention when fileKey is omitted, and the confirm-gate that returns a preview until confirm: true. It does not cover permissions or what a successful response contains, keeping it below 5.

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?

Four tight sentences, front-loaded with the purpose and field list, followed by the workflow and the two behavioral caveats. The trailing parenthetical is slightly clunky but is short and carries real information.

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 mutation tool with a nested audience object and no output schema, the description covers the critical unknowns: full-replacement risk, file retention, and the two-phase preview/confirm flow. Missing only edge details such as id validation or what the preview returns, which is a modest gap.

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 33%, so the description should compensate more. It names four of the editable fields and adds one real insight (absent fileKey preserves the existing file), but leaves id, title constraints, fileName/mimeType, and the nested audience object's meaning (all vs clientIds vs planIds) 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 ("Edit a library document") and enumerates the editable surface (title, category, link, audience), which separates it from create_library_item and delete_library_item without naming them. It does not explicitly name the mutating siblings, but the verb alone disambiguates.

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?

Prescribes a concrete workflow: fetch the current record with list_library_items, then change only what's needed. That is a genuine when/how-to-use instruction. It stops short of stating when-not to use it (e.g. create vs delete boundaries), so it is not a full 5.

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