bottle-details

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral context beyond that: Location/Bin are account-specific labels rather than physical descriptions, the default state='all' silently includes consumed bottles, and results are paged. It does not cover error/auth behavior, but the added context is substantial.

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?

Front-loaded with the identity of the resource, then filters, then the photo workflow, then the fallback, then pagination — a logical order. It is dense and long, but nearly every clause carries non-obvious information; only the enumeration of filter fields overlaps the schema.

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?

With an output schema present, the description needn't describe return values, and it doesn't. For an 8-parameter read tool it covers defaults, pagination, the photo/barcode path, and the account-specific-label edge case, leaving nothing an agent needs to call it 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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: state='all' is the default and includes consumed bottles, max_results defaults to 25 per page, offset pages through results, and barcode can be sourced from a photo. These are operational semantics, not restatements.

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 ('look up') and resource ('individual bottles from the Bottles table') and explicitly scopes it as the per-bottle view, distinguishing it from the aggregate siblings search-cellar and cellar-stats. An agent can tell what it returns (barcode, location/bin, size) without opening the schema.

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?

Gives explicit when-to-use conditions (filter by name/location/bin/size/barcode; state='cellar' vs 'all'), a concrete workflow for photo attachments (read barcode digits from image), and a named fallback ('use cellar-stats with group_by=location or group_by=bin') when a label filter returns nothing. Alternatives and exclusions are both covered.

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