list_tracked_skus

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

With no annotations, the description carries the full burden and does disclose the key behavioral fact that data comes from a bundled/static dataset rather than live pricing, plus that output counts weekly snapshots. It does not state read-only semantics explicitly, result ordering, or any size limits on the full listing.

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?

Three sentences, front-loaded with what the tool returns before the use cases. Every sentence contributes, though the "biggest-mover" clause slightly overpromises relative to a snapshot-count listing.

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 two-parameter discovery tool with no annotations and no output schema, the description covers purpose, data source, and discovery use cases but leaves open the semantics of since relative to the counts and what the unfiltered default listing looks like — both of which an agent needs to interpret results 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?

At 50% schema coverage the description must compensate partially. It clarifies that cloud is a scoping filter (not a required selector), but adds nothing about since — neither its default nor whether snapshot counts are computed within the date window, which is the most consequential ambiguity.

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?

"List every (cloud, sku) pair present in the bundled price-history dataset, with how many weekly snapshots exist for each" states a specific verb, resource, and return content, and names get_price_history as the downstream consumer, which cleanly separates it from the per-cloud price getters and compare_* siblings.

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?

It gives two concrete use cases (discovering callable SKUs for get_price_history, and finding biggest movers since a date) and names the relevant sibling. It stops short of saying when not to use it, and the "biggest-mover" framing is loose since the tool appears to return snapshot counts rather than movement magnitudes.

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