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

No annotations exist, so the description must disclose behavioral traits. It implies live data ('live discount') and conditional history, but does not state that it is read-only, whether it depends on authentication, or any rate limits or side effects. It lacks clarity on what happens without gpu_model (just the spread) and whether history is supplementary or exclusive. This is a significant gap given zero annotation support.

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 description is a single, compact sentence that front-loads the core concept (on-demand vs interruptible spread) and appends the optional history note. It is appropriately sized for the tool's simplicity, with no redundant words. The structure is efficient and easy to parse.

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?

Given no output schema and no annotations, the description leaves many gaps: what exactly is a 'spread'? How does the 'hours' parameter affect results? What does the tool return (discount percentage? rate per hour?)? The history behavior is only vaguely described. For an agent to call this correctly and interpret the response, crucial context is missing, making the description incomplete for its complexity class.

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 compensate. It explains that gpu_model triggers history, but does not explain the 'hours' parameter at all. The schema already shows defaults, but the description adds no meaning for hours (time window? granularity?). It partially covers gpu_model but leaves hours unexplained, which is insufficient for a 0-coverage tool.

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 states a specific concept: the live discount for idle capacity per model, contrasting on-demand vs interruptible pricing. It clearly identifies the resource (spot pricing spread) and the optional history behavior. It does not explicitly differentiate from sibling tools like idle_history or price_position, but the phrasing is sufficiently specific to avoid tautology.

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 description offers a usage hint ('pass gpu_model for its history too') but gives no guidance on when to choose this tool over alternatives. It does not mention exclusions, typical use cases, or relationships with siblings. An agent has to infer that this tool is for discount information, but no comparison to similar tools is provided.

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