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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real context beyond them: all values are 'Always scoped to the token uid', and it discloses the fallback rule (purchase price, or MSRP when no price was entered) plus that excludedCount bottles have no usable price. It does not state behavior for an empty shelf or any caching/rate considerations, so not a 5.

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 core definition, then tight clauses defining each output figure; nothing is wasted. The telegraphic fragments ('paid: ...', 'msrp: ...') are slightly cryptic in isolation but very information-dense and appropriate for a field glossary.

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 no parameters and no output schema, the description carries the return-value burden and largely meets it: it defines paid, msrp, excludedCount, totalCents (exact) and total (dollars). Minor gaps remain — no statement of currency edge cases or empty-shelf behavior — but an agent can call and interpret this 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?

Zero parameters, so the baseline is 4. The description nonetheless documents the effective inputs to the computation (the signed-in user's shelf, resolved from the token) and the MSRP fallback rule that determines the paid figure.

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 computed resource (the signed-in user's active shelf value in USD) with scope in parentheses (opened + unopened) and anchors it to a known reference ('the same number as the app's Stats'). This clearly separates it from list/get siblings that return individual bottles rather than an aggregate.

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 can infer this is for reading an aggregate total, and 'the same number as the app's Stats' hints at the matching display. No explicit when-to-use or when-not, and no alternative named (e.g. export_shelf or list_my_bottles for per-bottle data).

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