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

The annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The clause 'Fields left out stay the same' adds genuine patch semantics that the annotations do not provide, but the description never says what the destruction actually means (e.g. that an existing reply_text or priority ordering is overwritten) or whether the rule must be re-approved.

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, verb-and-resource first, identifier provenance second. Nothing is wasted and the most important constraint (omitted fields are preserved) is visible without reading further.

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 ten-parameter mutation tool with no output schema and only 40% schema coverage, the description covers the essentials of patching by id but leaves conditional dependencies unexplained, notably that 'when=keyword' is meaningless without keyword and that applies_to/reply_with take small value vocabularies. It is adequate to invoke safely on the happy path but thin for edge cases.

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 40%, so several of the ten parameters (keyword, priority, skip_approval, active) have no documented meaning anywhere, and the description does not compensate for that gap. It does explain why every optional field accepts null (leave unchanged) and where rule_id originates, which is real added meaning over the schema's circular 'The rule_id.'

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 a specific verb and scope: 'Changes one auto-reply rule', which separates it from create_auto_reply_rule and delete_auto_reply_rule. It also points to the sibling that supplies the required identifier, so the agent knows which tool precedes this one.

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 parenthetical '(rule_id from get_auto_reply_settings)' is implicit guidance to call the read tool first, which is useful context. However, there is no explicit when-to-use/when-not framing and no warning that this is not the tool for creating rules or changing account-wide defaults via set_auto_reply.

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