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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add operational context. It does: the numbers reproduce drxinfra.ru/sizing.html exactly and a link back to that calculation is returned — behavior an agent could not infer from the annotations or schema.

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?

Three sentences, front-loaded with what the tool returns before the provenance and caveats. The parenthetical role list is long but earns its place by telling the agent what the output covers.

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?

For a 26-parameter, zero-required sizing tool with no output schema, the description covers what is produced, where the numbers come from, the result link, and the default-parameter behavior. A brief note on the output shape (per-role table vs totals) would close the remaining gap.

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 26 parameters at 100% schema description coverage, including enums, defaults, ranges and cross-parameter constraints (k8s only with place=k8s, pgKind only with db=pg), the schema carries essentially all parameter meaning. The description only adds the global fact that omitted parameters fall back to page defaults, which is the baseline 3 case.

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 output (servers, vCPU, RAM, disks) for a specific product (Directum RX) broken out by role, and names the exact reference model it reproduces. This is easily separable from siblings like size_ai or component_versions without opening the schema.

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 a usage boundary ('an estimate for budget and requirements, not a load test') and tells the agent the call is safe to make with no arguments because every parameter is optional with page defaults. It does not, however, say when to prefer size_ai or upgrade_checklist instead.

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