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

With no annotations, the description carries the full burden and does real work: it warns that HTTP success is not proof of on-chain completion, and that credentials, charges, and authorization flow through the OpenAny gateway. It omits that retrieval itself is non-mutating and whether the call is billed on its own, but the operational risks it does disclose are the ones an agent could not guess.

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?

Five short sentences, front-loaded with the core action, and the most important caveat about on-chain proof appears early. The series of fragments ('Uses the native public Uniswap HTTP contract') is slightly staccato but nothing is wasted.

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 three-parameter read tool with no output schema, the description tells the agent what it is fetching and what success does not mean, but it never indicates what a plan contains (steps, statuses, quotes) or how to act on a returned plan. That leaves an agent guessing about the return structure.

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 planId and forceRefresh are already documented, including the 'completed plans cannot be refreshed' constraint. The description adds nothing about parameter meaning, so the baseline of 3 applies.

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 uses a specific verb plus resource ('Get an execution plan'), and the parameter set confirms it retrieves a single plan by identifier. It does not explicitly contrast with the sibling mutation tools (uniswap_post_v1_plan, uniswap_patch_v1_plan_planid), but 'Get' versus 'post/patch' makes the read-versus-write split inferable.

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?

Usage is implied rather than stated: an agent can infer this is how you poll or inspect an existing plan, but the description never says when to call it versus creating or patching a plan, nor when to set forceRefresh. No alternatives or preconditions are named.

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