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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description does add real behavioral context beyond that: the constant-product 50/50 model assumption, that it compares LP against holding, and that it layers in simple fee income and a break-even fee APR. However, it says nothing about assumptions or limits (e.g. that fees are 'simple', not compounded) beyond that single adjective, nor about the response.

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 first sentence is dense, front-loaded, and earns its place. The following four sentences are generic boilerplate about field placement and schema compliance, and two of them reference fields ('units', a REST calculator field) that do not appear in the input schema, adding noise instead of signal.

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?

An output schema exists, so return values need not be explained, and the annotations cover safety. But for a tool with a six-property nested inputs object at 0% schema coverage, the description leaves key parameters (days, deposit, fee_apr_pct, start_price/end_price vs price_change_pct) undefined, and its references to nonexistent 'units' and REST fields reduce confidence. It is minimally adequate but incomplete.

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 a nested inputs object with six sub-fields (days, deposit, start_price, end_price, fee_apr_pct, price_change_pct), so the description must carry the burden. It explains only 'r is the price ratio change', which partially maps to price_change_pct, and never explains the start_price/end_price alternative, days, deposit, or fee_apr_pct. Worse, it tells the agent to 'supply units' when no units field exists in the schema, and warns against a 'REST calculator field' that is also absent, which invites confusion rather than clarity.

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 names a specific resource and computation: impermanent loss for a 50/50 constant-product pool, with the exact formula IL = 2*sqrt(r)/(1+r) - 1 and the price-ratio definition. It also states the outputs (LP vs holding comparison, fee income, break-even fee APR), so the agent knows precisely what it gets. It does not differentiate against siblings, but the siblings listed are unrelated calculators, so this is a minor gap.

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 when-to-use or when-not-to-use guidance, and no named alternative. The only directional text ('Put tool fields inside inputs', 'Follow its required fields') is invocation mechanics rather than tool selection guidance. An agent must infer that this is the right tool for LP-vs-holding analysis purely from the name and formula.

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