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

The annotations already declare readOnlyHint=false and destructiveHint=true, and 'Update' is consistent with that. The description adds the useful field surface that can change, but for a destructive mutation it never clarifies merge-vs-replace semantics (does passing pieceIds overwrite the existing selection?), whether omitted fields are preserved, or what happens to pieces shared through the style.

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?

Two short sentences with the actionable content front-loaded and no filler. The second sentence is terse to the point of being cryptic — it states that part-specific pieces differ from style-shared pieces without saying what the agent should do differently, so it earns its place but is under-exploited.

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?

This is a destructive, nested-object mutation with 0% schema description coverage and no output schema, so the description should do more work. It omits partial-update semantics, the meaning of the mirror/requires relationships, and whether the updated part is returned — gaps an agent must guess at before calling.

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% and the nested 'updates' object has five undocumented fields, so the description must carry meaning: it does map loosely onto name, position, pieceIds and the two relationship fields (mirror/requires). However, it never names mirror_part_id or requires_part_id, gives no format or constraint detail (the 100-item cap on pieceIds), and leaves the replace-vs-append question unanswered.

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 opens with a specific verb plus resource ('Update a part') and enumerates the mutable surface: name, position, relationships, and selected piece IDs. That is enough to separate it from create_part, get_part, and list_parts without opening a schema, though it never names a sibling explicitly.

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 rather than stated: an agent infers this is the tool for modifying an existing part and that piece assignment is handled here. There is no explicit when-not guidance (e.g., use create_part for new parts, update_style for style-level pieces), and no prerequisites such as needing an existing partId.

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