resolve_defi_intent

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds the compatibility/legacy behavioral constraint, which is real value, but says nothing about what is returned, how a resolved intent is consumed downstream, or auth/tier implications of "paid_ready".

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 bracketed prefix ("Capability: paid_ready; tier: pioneer_plus; API: /api/v1/agent/intent; authority: /api/v1/agent/status") is internal bookkeeping that consumes the front-loaded position without helping tool selection. Only the final two sentences carry actionable content.

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?

A 13-parameter tool with a nested object, one enum, no output schema and no parameter docs needs far more description than two sentences. The agent cannot tell which required fields are conditional on action (tokenOut/amountOut for swap, poolAddress for liquidity) or what the constraints object gates.

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% across 13 parameters, including a nested constraints object with six undocumented fields (maxGasUsd, minAmountOut, positiveNetEdge, etc.) and an action enum. The description supplies zero parameter meaning, so the agent must infer all semantics from names alone.

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?

"Resolve a legacy typed DeFi intent" gives a verb and resource, and the word "legacy" distinguishes it from the newer create_intent lifecycle. But "resolve" is ambiguous (quote? plan? execute?) and the leading metadata block about capability tiers and API paths adds no meaning about what the tool does.

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 second sentence explicitly routes new state-changing work elsewhere: create a durable FarmDashIntent (create_intent) and go through policy/simulation/approval (policy_check_intent, simulate_intent, request_approval_payload). That is a clear when-not-to-use with named alternatives, though it never says when resolving a legacy intent is actually the right call.

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