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

Annotations already declare non-read-only, open-world, idempotent, non-destructive. The description adds real behavioral content they don't carry: reviews are persisted when found, update_identity overwrites name/distillery/proof, and the flow is two-step. The overwrite of identity fields vs. destructiveHint=false is not reconciled, but the disclosure is substantive.

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, action and consequence front-loaded, no filler. The trailing fragment 'Two steps.' is terse to the point of being cryptic and depends on the schema to be understood, which keeps it just below top marks.

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 mid-complexity, mutating, two-step tool with no output schema and annotations covering the safety profile, the description covers purpose, side effects, and the conditional identity update. The main gap is that it never says the first pass returns a preview and a cost, leaving that entirely to the confirm_token schema.

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?

With 50% schema coverage, the description compensates meaningfully: it explains update_identity's effect (replace name, distillery, proof) far beyond the schema's bare default, and the two-step 'Two steps.' aligns with the confirm_token workflow. It adds nothing for bottle_id, which is required but undocumented in both places.

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 combined action: re-identify an owned bottle from its photo and research fresh reviews. The phrase 'one of your bottles' scopes it to bottles the user already owns, which distinguishes it from add_bottle_from_photo and lookup_bottle. It stops short of naming a sibling explicitly, so it is clear but not fully differentiated.

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?

'Think harder about one of your bottles' implies a re-run/escalation context when a prior identification was unsatisfactory, and 'pass update_identity to also replace...' gives a conditional branch. But there is no explicit when-to-use/when-not or named alternative (e.g., lookup_bottle, get_my_bottle), so the routing signal is implied rather than stated.

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