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

Adds substantial context beyond the readOnlyHint/openWorldHint annotations: no server-side history, per-request point deduction proportional to token usage including compaction processing, and a 5P base per request. It does not cover error/failure behavior or rate limits, so it stops short of fully transparent.

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 stateless/history rule and the model-lookup pointer are front-loaded, which is good, but nearly every sentence is duplicated in English and Korean, roughly doubling length without adding information. The billing bracket note at the end is also terse to the point of being cryptic.

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 an 8-parameter tool with a nested compact object and no output schema, the description covers the state model, history protocol, compaction role, and cost, which are the non-obvious parts. Response shape beyond compacted_messages and failure modes are left undocumented, but the essential calling contract is present.

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 the baseline is 3; the description earns above that by explaining the multi-turn contract — the response's compacted_messages is fed back verbatim as the next call's messages, a return-value detail absent from the input schema. The content-vs-messages precedence and compaction tradeoff are also reinforced rather than merely restated.

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: send a chat request to a selected LLM model and receive the assistant reply. It also distinguishes itself from the sibling llm_models by naming that tool as the model-lookup path, so an agent can route correctly 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?

Gives clear operational context: the server is stateless, so every call must carry the full history in messages and reuse the response's compacted_messages on the next turn, and available models come from llm_models. It does not say when to prefer this over LLM-adjacent siblings such as text_polish or text_summary, leaving that to inference.

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