compare_yields

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds the useful fact that this is a research/read operation gated to a 'paid_ready; tier: pioneer_plus' capability with a specific API surface, but it does not say what the comparison output contains or how results are ranked/paged.

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 substantive content is a single efficient sentence that front-loads the verb and resource. The bracket-prefixed capability/tier/API/authority metadata consumes roughly half the string and delivers little value an agent can act on when selecting or invoking the tool.

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 7 optional parameters, no output schema, and no required fields, the definition must convey filtering behavior and return shape. It names comparison dimensions but says nothing about default limits, filter combination semantics, or what a result entry looks like, leaving real gaps for a research tool with this many knobs.

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 7 parameters, so the description is the only source of semantics. It loosely hints at minTvlUsd ('TVL depth'), stableOnly ('stablecoin exposure'), and riskPreference ('IL risk', 'sustainability'), but leaves assets, chains, projects, and limit completely unexplained, and never maps named concepts to the actual fields.

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 verb and resource ('compare DeFi yield pools') and enumerates the comparison dimensions (APY, TVL depth, stablecoin exposure, IL risk, sustainability score). This clearly separates it from action-oriented siblings like simulate_yield_strategy or prepare_intent, though the bracketed capability/tier/API metadata prefix adds noise rather than clarity.

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 'Research:' label implicitly signals this is a read-only analysis step rather than an execution step, which helps position it against execution siblings. However, it never states when to choose this over simulate_yield_strategy, get_protocol_risk_factors, or scan_market_conditions, nor does it mention prerequisites like tier/authority for the paid capability.

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