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

With no annotations, the description carries the full behavioral burden and does reasonably well: it discloses the decision vocabulary with reason codes, that buys weigh risk flags, Degen trenches signal and exit momentum while sells run the exit verdict, and the snapshot-window override. It does not state whether the call is read-only or executes anything, nor any auth or rate limits, leaving a notable gap for a pre-trade gate.

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?

Three sentences, each load-bearing: what to pass and what comes back, what the verdict is computed from, then the time-window exception. The return vocabulary and the exception are front-loaded and nothing is repeated from the schema.

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 6-parameter tool with no output schema, the description supplies the return contract (PROCEED/REDUCE/HOLD plus reason codes) and the key edge-case rule. What is missing is the read-only/execution status and the network parameter's effect, both of which matter before an agent wires this into a live send flow.

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 the baseline is 3; the description still adds meaning by naming the four required fields as the intent payload and by explaining that the seasonEndsAt snapshot drives a hard behavioral rule. It does not clarify the network parameter or the mainnet/devnet implication for the advice.

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 description states a specific action and resource: pass a pending swap intent (category, tokenInMint, tokenOutMint, amountIn) and receive PROCEED/REDUCE/HOLD. It is clearly a pre-send gate rather than an analytics feed, which separates it from siblings like exit_signal or trenches_check, though no sibling is named explicitly.

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?

"Pass the swap intent you are about to send" clearly establishes the moment of use, and the description adds a temporal rule (within 60 min of the season-end snapshot, sells proceed and buys hold). It gives no explicit when-not-to-use guidance or named alternatives, so it stops short of a 5.

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