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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added contribution is the 'never live; nothing is fetched' disclosure, which tells agents this tool performs no network I/O and returns cached data. This is meaningful behavioral context beyond the structured hints.

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 compact sentences with no filler; the field list is front-loaded and the freshness caveat follows. Every clause adds information needed to invoke or interpret the tool.

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 parameterless, read-only list tool, the description supplies both the return contents and the data-freshness caveat. No output schema is present, but the enumerated fields make the response shape predictable.

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?

The tool has zero parameters, so there is no schema semantics for the description to supplement. Baseline 4 is appropriate because the description adds no parameter claims but none are needed.

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?

Opens with 'Show every tracked item with current and previous price...' – a specific verb, resource, and exact field list. It clearly identifies this as a read-only listing tool and differentiates it from mutation siblings like watch_add, watch_remove, and watch_refresh by emphasizing 'nothing is fetched.'

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 caveat that prices are as of the last watch_refresh and never live gives agents clear context for when this cached view is appropriate. It does not name alternatives or state exclusions, but the staleness warning is sufficient guidance for a simple list operation.

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