yield-optimizer

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful behavioral context beyond them: data is read live from the chain, cross-checked against each market's own rate model, and returned ordered best-first with a named leading field.

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?

Only two sentences, but the 'free half / paid half' metaphor consumes roughly a third of the text without adding concrete information an agent can act on. The substantive content (scope, provenance, ordering) is present but not maximally front-loaded.

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?

With no output schema, the description does the work of describing the return: supply rates for every market, ordered best-first, with venus_usdt_rate_pct at the top. It stops short of stating the container shape (list vs object), refresh/caching behavior, or whether any chain other than BNB is covered.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate; the baseline for a zero-parameter schema is 4. No misuse risk from omitted argument semantics.

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 scope: the supply rate of every Venus market on BNB Chain, sorted best-first, with the leading field named. The 'free half' framing implicitly distinguishes it from the sibling yield_plan, though the sibling is never named directly, which keeps it short of a 5.

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: this is the 'free half' (raw rates), while 'the paid half' addresses whether moving your deposit pays for itself. No explicit 'use this when...' condition, no exclusions, and the sibling yield_plan is never named, so the agent must infer the routing.

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

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the important extras and does so: it discloses the paid/x402 gating and escrow flow, plus the computation methodology (per-block rate, chain-measured block time, re-derivation from borrow rate/utilisation/reserve factor). That is meaningful behavior beyond the annotations, though the return format beyond the two-sentence promise is not fully spelled out.

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 text is one sprawling multi-clause paragraph with parenthetical asides and em-dashes; the core value proposition is not front-loaded and the payment terms are tangled with the methodology. It is over-long and hard to scan.

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?

With no output schema, the description must explain returns, and it does: ranked rows, an agreement summary naming divergences, and the days-until-break-even figure. The payment/escrow gating is also covered. It is complete enough to call correctly, though the verbose packaging makes the key facts harder to extract than they should be.

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% for the single 'task' string, so the baseline is 3. The description hints at required inputs ('an amount and what you earn today') that the schema does not model, adding marginal meaning, but it does not clarify the task string's format beyond the schema's 'with the address in it'.

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 analysis: ranking Venus core-pool markets by supply APY and computing whether a position move pays for itself. However, the purpose is buried mid-paragraph in run-on prose, and it never explicitly distinguishes itself from the sibling venus_supply_rates (ranking/break-even vs raw rates).

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 clear statement of when to use this tool versus venus_supply_rates, nor any when-not guidance. The only routing signal is the payment note ('Calling this tool returns the terms; the answer is sold over x402'), which tells the agent about cost but not task suitability.

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