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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely new context that annotations cannot carry: the call is paid at 0.10 USDC, which affects whether an agent invokes it speculatively. It stops short of describing auth requirements or what a 'stress score' means.

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 clauses, pricing and subject front-loaded, with zero filler. The cost warning sits first where an agent will see it before deciding to call.

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?

Output schema exists, so return values need not be explained, and the single parameter is fully covered by the schema. However, the central domain concept ('capacity stress score') is left undefined and the crowded capacity sibling set is never disambiguated, leaving the agent to guess which capacity tool answers its question.

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% — the single 'day' parameter already documents YYYY-MM-DD format and default-latest behavior. The description only restates the one-day scope, adding no format or edge-case detail beyond the schema, which is the expected baseline.

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 (every GPU model's capacity stress score), a scope (one day), and an ordering (tightest first), so an agent knows exactly what comes back. It does not distinguish itself from near-named siblings such as capacity_stress, capacity_headline, or capacity_history, which is the only missing piece.

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?

No when-to-use or when-not guidance, and no routing to alternatives despite three closely related capacity siblings. 'For one day' faintly implies this is the daily snapshot rather than history, but that is inference, not guidance.

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