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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, and the title states it spends credit, so the risk profile is largely covered structurally. The description contributes the additional detail that the charge can come from either the Phase API key or the wallet, which annotations do not say. It does not specify any cost magnitude, rate limits, or whether a failed call still bills, leaving meaningful behavioral gaps.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though the brevity borders on under-specification rather than tight precision.

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 metered, destructive, non-idempotent call with an undocumented input parameter, the definition is too thin: no cost signal, no note on where model ids come from, and no hint that input is an array of strings. The presence of an output schema excuses it from describing return values, but the rest of the calling context an agent needs 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 description coverage is only 50%: model carries a terse "embeddings model id" while input (a nullable array of strings) is undocumented in both schema and description. The description adds nothing about input shape, batching, or how to obtain valid model ids, so it fails to compensate for the coverage gap.

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?

Names a specific verb and resource ("Compute embeddings") on a named service (Phase Router), which cleanly separates it from siblings like chat, quote, and session that handle other router operations. It stops short of any explicit differentiation sentence, but the resource is distinctive enough that an agent can identify it 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?

There is no guidance on when to pick this tool over alternatives such as list_models (for discovering valid model ids) or quote (for checking cost) before spending. The only contextual clause, about being paid from the API key or wallet, is billing information rather than usage direction, so the agent must infer the decision rules.

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