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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds value beyond that with patch semantics ('Only the fields you pass change') and an author/admin permission rule for shared replies, though it never says what 'destructive' actually means here (e.g. tag replacement or overwriting).

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?

Three short sentences, zero waste, and the core action is front-loaded before the partial-update and permission clauses.

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 no output schema this covers the essentials: what changes, that it is a partial update, and who may change a shared reply. Missing only edge behavior - tag replacement semantics, the item limit, and whether other users are affected.

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 20% (just savedReplyId), so the description must compensate - and it does by naming the four updatable fields and mapping them to the optional parameters, plus clarifying that omitted fields are untouched. It still omits details like the 10-tag cap or the 'sharing' vs 'shared' naming.

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 ('Change') and resource ('a saved reply') and enumerates the mutable fields (title, body, tags, sharing), which distinguishes it from create_saved_reply, delete_saved_reply and render_saved_reply. It does not name any sibling explicitly, but the operation type is unmistakable.

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 by the mutation verb rather than stated. The one real guideline is a precondition - 'A shared reply is changed by its author or an admin' - which is useful context, but no alternatives (e.g. save_reply_draft, draft_reply_with_ai) are named or contrasted.

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