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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful non-obvious detail: each verdict carries the exact file and format, the runtime, the measured speed, and a provenance tag distinguishing Kingy-measured from third-party-reported from estimated — which tells the agent how much to trust the answer. It does not describe the response shape or behavior for unknown models beyond the 'Not tested yet' verdict.

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 sentences, front-loaded with the verdict concept before the supporting detail about file/format/runtime/provenance. Dense but every clause carries information; the parenthetical machine list is slightly long but earns its place by defining the enum domain.

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?

There is no output schema, so the description must carry the return-value burden, and it does: verdict tiers, per-machine results, file/format, runtime, speed, and provenance. For a simple two-parameter lookup this is close to sufficient; only the unknown-model / no-data path is left implicit.

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 coverage is 100%, so baseline would be 3, but the description goes further by glossing the six enum values in human terms (16GB laptop, 24GB/32GB GPU PC, 64GB Mac, 128GB Mac or Strix Halo, 512GB Mac Studio), which materially helps the agent map a user's hardware to an enum value. It adds no guidance on the model string format, which the schema already handles with an example.

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 opens with a specific verb+resource: a verdict on whether a model runs on your own hardware, and enumerates the exact verdict scale (Yes, Yes but slow, Barely, No, Not tested yet) plus the machine buckets. No sibling tool (check_model_access, get_model_prices, etc.) covers local-run feasibility, and the description makes that distinction obvious without opening either 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?

Usage is strongly implied by the purpose ('should you run it at home?'), and the machine parameter's 'omit for all' behavior is clear. However, the description never explicitly contrasts this with the nearest sibling, check_model_access, which an agent could plausibly confuse with a 'can I run this' question; there are no stated exclusions or antecedents.

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