get_price_changes

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the backing endpoints, the ordering (newest first), the daily refresh cadence (~10:23 UTC), and that the response carries data_checked_at and next_refresh_utc for staleness reasoning. That is meaningful operational context an annotation cannot convey; only the unexplained 'mode' parameter keeps it from 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?

The lead sentence front-loads the resource and output shape, followed by parameter behavior in decreasing order of importance. It runs long and the parenthetical endpoint paths are somewhat noisy, but each clause carries usable information rather than filler.

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 a read-only annotation set and an output schema already present, the description doesn't need to enumerate return values, yet it helpfully names the key fields and freshness markers. The single real hole is that 'mode' has no explanation anywhere, which for a 4-parameter tool is a modest but genuine gap.

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 description coverage is 0%, so the description must carry the load and it does for three of four params: gpu is a substring filter with an 'H100' example, limit is bounded 1-200, and since has both format and semantics. The 'mode' parameter (default 'full') is never mentioned, leaving one documented-in-neither-place argument that an agent must guess at.

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?

The description opens with a specific verb+resource: 'GPU rental price changes among tracked providers, newest first, each with old/new hourly price, change_pct, direction and the vendor source_url.' That distinguishes it from the snapshot-oriented siblings (compare_gpu_prices, search_deals), though it never names an alternative explicitly, so differentiation is inferred rather than stated.

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 clearly states the conditional behavior of the two main arguments: since='YYYY-MM-DD' returns every change on or after that date, while omitting it returns only the latest day's moves. It also explains when to call again ('call again after the next refresh to see what moved'), giving the agent a polling strategy. What's missing is explicit routing against siblings like compare_gpu_prices.

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