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

Annotations already provide readOnlyHint=false (mutation) and destructiveHint=false (not destructive). The description adds key behavior: content edits create a new version, document type does NOT change, and content format handling (markdown vs HTML). This goes beyond annotations and is critical for agent expectation. No contradiction, though it could mention if title edits also create versions (unclear), but that's a minor 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?

The description is concise: two sentences then an Args list. It front-loads the purpose and version behavior. The Args list is clean and matches schema parameters. Every sentence adds value—the format guidance for content is essential. No fluff or repetition.

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?

The tool has an output schema (not detailed in the prompt, but present), so return values need not be explained. With 3 params, the description covers the behavior of each. It doesn't mention error cases (e.g., invalid item_id) but that's not typically required. The versioning behavior is explained well. Missing: whether title-only updates create versions, but that's minor. Overall, sufficient for an agent to call correctly.

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 0%, so description must compensate. The description explains that 'title' and 'content' are optional and lists their semantics (title vs content). It clarifies that content is markdown or HTML. However, it doesn't explain 'item_id' beyond being a UUID, but the schema name 'Item Id' and required status are self-explanatory. Baseline for low coverage is 1, but description adds meaningful detail, hence 3.

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 states a specific verb ('Update') and resource ('library document'), and clarifies scope: title and/or content, with content edits creating a new version. It differentiates from siblings like 'create_library_item' and 'delete_library_item' by implying this is for existing items, and from 'list_library_item_versions' by noting version creation. The 'versioned' in title is reinforced by the description.

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 description clearly indicates when to use it: to modify an existing library item's title/content, and implies not for creating or deleting (siblings exist). It mentions content handling for markdown vs HTML, which is a context-specific instruction. However, it doesn't explicitly state when NOT to use it or name alternative siblings for creation/deletion, but the context signals include those siblings and the purpose is clear.

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