capacity_plan

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds real value with the disclaimer 'No service sizing guarantee', telling the agent the output is arithmetic, not a provisioning recommendation. It does not state determinism, rounding, or unit conventions, so it stays at a solid but not rich 3.

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, front-loaded with what is computed, followed by the one caveat that matters. No filler, no restatement of the tool name, and the qualifier is placed where it will be read before calling.

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 need no explanation, and annotations carry the safety profile. But for a pure-calculation tool the critical missing piece is what the inputs mean and in what units, and with 0% schema coverage the description leaves all four required parameters undefined, including the non-obvious headroom multiplier.

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% and all four parameters are required, yet the description never names or explains any of them. 'Traffic assumptions' gestures vaguely at requestsPerSecond and payloadKB, but the meaning of headroom (a 1.0-10.0 multiplier defaulting to 1.3) and the units/limits of durationMs are left entirely to inference.

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 (Calculate) and two specific outputs (concurrency and daily data volume) plus the input class (explicit traffic assumptions). It implicitly separates itself from siblings like storage_growth or latency_budget, though it never names a sibling to sharpen the boundary.

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?

There is no explicit when-to-use, when-not-to-use, or named alternative. The phrase 'from explicit traffic assumptions' hints that the caller must supply measured or assumed traffic rather than deriving it, but an agent has to infer that, and nothing says when capacity_plan should be chosen over queue_sizing, latency_budget, or cost_model.

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