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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses two non-obvious behaviors: the no-argument listing mode and that results include which GPUs fit an estimate plus their current price. It omits error behavior (e.g., unknown model names) and any rate limits.

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?

The purpose is front-loaded in the first clause and the discovery-mode tip closes efficiently in a second sentence. The long parenthetical listing model families is informative but slightly bloats an otherwise tight definition.

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 read-only calculator with no output schema, the description covers what the tool does, its optional-argument mode, and that results pair GPU fit with pricing. A short note on how unknown models are handled is the only material 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?

Schema description coverage is 100%, so defaults and value ranges for all four parameters are already documented in the schema. The description only gestures at 'a given precision and context length' and never mentions concurrent_requests, adding nothing beyond the structured fields. Baseline 3 applies.

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 and resource ('estimate' GPU memory for an AI model) and enumerates the model families it covers, so its scope is immediately legible. It is clearly distinguishable from siblings like list_gpu_models and search_offers, which list rather than compute.

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 an explicit conditional behavior: 'Call without `model` to list the known models,' which tells the agent how to use it in discovery mode versus estimation mode. It does not name alternative tools or state when another sibling (e.g., search_offers) should be preferred instead.

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