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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuinely useful non-annotation context: the call is metered at 0.05 USDC per call, which materially affects how an agent should plan invocations. It stops short of explaining result granularity or limits, so not 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?

Two short sentences with zero filler, and the cost constraint is front-loaded so the agent sees the billing implication before anything else.

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 values needn't be described. Combined with full schema coverage and rich annotations, the description covers scope and cost; the only real omission is the default behavior when from/to are omitted.

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 100% (gpu with an H100 SXM example, from/to as YYYY-MM-DD), so the schema already carries parameter meaning. The description only echoes the single-GPU scoping and adds no date-range or format detail, which is the correct baseline of 3 when the schema does the work.

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 resource and scope: 'Daily capacity stress scores for one GPU model.' Combined with the name, an agent knows this returns historical time-series stress data scoped to a single GPU. It does not, however, distinguish itself from near-siblings like capacity_stress, capacity_board, or capacity_headline, which is the only thing keeping it from a 5.

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 gives no when-to-use guidance: it never says to reach for this instead of capacity_stress (current) or capacity_board, nor does it explain the intent of the from/to range. The pricing note is cost context, not usage routing, so the agent must infer selection from the name alone.

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