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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds that this reflects currently provisionable hardware (a point-in-time snapshot implied), but discloses nothing about freshness, caching, or response shape.

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 tight sentences with the core purpose front-loaded; the REST endpoint reference is compact and useful for debugging. No filler, though the endpoint detail is marginally redundant for an agent.

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 simple, zero-required-parameter read tool with full schema coverage and no output schema to explain, the description covers what is needed to invoke it. Only the when-to-use context is missing.

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 both filters (source, base_model) are documented in the schema. The description adds no syntax, allowed values, or interaction detail beyond the schema, so the baseline of 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 ('Get GPU availability') and clarifies the meaning of availability with '(which hardware can currently be provisioned)', which an agent can act on. It does not, however, distinguish itself from the sibling deepinfra_get_hardware, so the agent must infer 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?

The description says what the tool returns but never when to call it versus alternatives such as deepinfra_get_hardware or before deepinfra_start_deployment. No prerequisites, no exclusions, no routing guidance.

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