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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds that results come from a 'live TokenOS roster' and include 'price multipliers,' which is useful output context, but says nothing about ordering logic, freshness, or result 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?

One front-loaded sentence with no padding. The modifier stack 'best, balanced and cheapest' is slightly muddled since those criteria can conflict, but the sentence remains compact and readable.

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?

With no output schema, the description partially compensates by hinting returns include price multipliers, but does not describe the recommendation structure or ordering. For a low-complexity, single-optional-parameter tool with rich annotations, this is adequate but not complete.

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% for the single 'task' parameter, so the description must carry the burden, and it only loosely implies the parameter is a build-task description. It gives no format, expected content granularity, or note that the parameter is optional despite being the only input.

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 verb 'Pick' and resource 'models' are specific, and the scope ('best, balanced and cheapest frontier models from the live TokenOS roster for a build task') is concrete. It does not, however, differentiate itself from the siblings plan_dapp or tokenos_capabilities, so an agent cannot tell from the text alone when this is preferable to those.

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?

'for a build task' implies the usage context, so the when-to-use is inferable. There are no exclusions, prerequisites, or named alternatives (plan_dapp, tokenos_capabilities) to route the agent, leaving the choice between siblings to inference.

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