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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new behavior: capped at 50 cheapest matches, 'no account or delivery subscription is created,' and an RSS feed alternative for ongoing polling. That is useful context beyond the structured fields, though it omits rate-limit or freshness/caching behavior.

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 qualifying condition is front-loaded and each sentence conveys a distinct fact (filters, model_slugs default, 50-cap, no subscription, RSS alternative, warnings). It is slightly dense at six sentences but there is little obvious padding.

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?

An output schema exists, so return-value documentation is not required, and the description does cover the core semantics and an RSS alternative. But for a 23-parameter, low-coverage tool it leaves most of the filter space unexplained, so an agent must infer parameter behavior from the schema alone.

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?

With 23 parameters and only ~22% schema description coverage, the description carries the compensating burden but only clarifies baseline_usd, minimum_saving_usd, and model_slugs. The many other parameters (route_type, execution, retry_percent, cache hit/write percents, benchmark_id, required_capabilities, etc.) receive no explanation in the description, leaving the majority of the surface undocumented.

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 verb and resource ('Read current offers') and defines the qualifying condition in terms of the two required params (monthly baseline_usd minus minimum_saving_usd). It also relates itself to the sibling offer_compare by sharing the same workload/qualification/evidence filters, which helps an agent place it. It stops short of a crisp one-line differentiator versus offer_compare, but the purpose is unmistakable.

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?

Gives actionable usage hints: 'Omit model_slugs to watch all qualifying models' and 'Inspect offer warnings before switching,' plus a note that the same query is available as RSS so a reader handles polling. However, it never states explicitly when to pick price_watch over the sibling offer_compare, nor any when-not conditions; the guidance is implied rather than spelled out.

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