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

Beyond the readOnly/openWorld annotations it discloses data provenance (daily snapshots at /history.json, latest-day at /price-changes.json), refresh cadence (~10:23 UTC daily) and freshness fields (data_checked_at, next_refresh_utc). It also explains pagination semantics (ordering differs between since and cursor modes), a stable dedupe key, and an error-recovery path for expired cursors — exactly the operational context annotations cannot convey.

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?

Dense but front-loaded: the resource is stated first, then the parameter playbook in the order an agent would use it, with no filler sentences. The only mild redundancy is enumerating returned fields even though an output schema exists, but it is one clause and aids dedupe reasoning.

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 rightly focuses on pagination, ordering, freshness windows and error recovery rather than return shapes. Combined with annotations, an agent can call this correctly end-to-end. The undocumented `mode` parameter is the one thing left for the agent to infer.

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 carries the full burden and it delivers formats and semantics for `since` (YYYY-MM-DD, inclusive, newest-first), `cursor` (opaque, from next_cursor), `kinds` (enum subset down/up/new/removed/same), `gpu` (substring, example 'H100') and `limit` (1-200). The `mode` parameter (default 'full') is never mentioned anywhere, which is a real gap in an otherwise strong parameter explanation.

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 opening sentence names a specific resource and view: GPU rental price changes across tracked providers, plus the exact fields returned (old/new price, change_pct, direction, source_url, event_id, rate_id). It is unmistakably a change-feed rather than a comparison or deal tool. It stops short of naming any sibling tool or explicitly excluding a comparison-style call, so it is clear but not sibling-differentiating.

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 concrete when-to-use rules for both retrieval modes: `since` for a date-windowed backfill, `cursor` for incremental continuation, including the rule to loop until has_more is false and to persist next_cursor only after processing. It also tells the agent what to do on cursor_expired (re-sync with since, dedupe by event_id). No guidance on when a different tool (e.g. a comparison tool) is the better choice.

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