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

Beyond annotations, it discloses that markets with no matching category are omitted, that unfiltered queries return every category on every chain, and that responses can be large enough to make 'symbols' strongly preferred. There is no contradiction with the read-only annotation.

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 description is focused and every sentence earns its place: version gating, eMode behavior, return fields, filtering advice, and the v4 exclusion. There is no repetition of schema content and no filler.

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 compensates by itemizing the returned fields (categoryId, LTV, liquidation thresholds, symbols) and explaining the omission behavior. It also covers parameter behavior and version constraint, leaving an agent with enough to invoke it correctly.

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%, so baseline is 3, but the description adds meaningful semantics: symbols is case-insensitive and strongly preferred for large chains, chainId omission covers all chains, and the return value includes the categoryId that feeds prepare_set_eMode plus LTV and thresholds.

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 ('eMode categories'), a specific verb ('Returns'), and the exact scope ('v3 only'). It distinguishes itself from siblings by explicitly calling out prepare_set_emode as the consumer of its categoryId and by noting v4 has no eMode.

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?

It gives clear when-and-how guidance: use it to discover eMode categories, LTV, and thresholds for v3, narrow the response with 'symbols', and omit chainId for all chains. It also says v4 should not use this tool, but it does not explicitly name other tools as alternatives for non-eMode reserve data.

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