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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false. The description adds genuine context beyond that: the call is free, it dispatches to stateful actions (quote, negotiation, redemption), and it returns reply text plus structured data. It stops short of saying which paths mutate state or require the wallet, which matters given a non-read-only, non-idempotent profile.

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?

Three sentences, front-loaded with cost and the core instruction, then the intent list, then the return shape. The parenthetical intent catalog is dense but each item maps to a real capability; little 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?

Three parameters at full schema coverage, an output shape stated inline (no output schema exists), and a closed-world, non-destructive annotation profile. What is missing is side-effect disclosure: whether sending a counter-offer or redemption message commits anything irreversible, and when the optional wallet becomes required.

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% and each parameter is already documented, so the baseline is 3. The description still adds meaning by specifying what belongs in `message` (intent classes) and giving a concrete feedback syntax ('helped h_...'), which is content guidance the schema string does not supply.

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 clear verb+resource: send a free-text message to AETHER, which infers intent and performs the appropriate action. It enumerates the intent classes it accepts (need, question, price request, counter-offer, receipt, partnership, feedback) and the resulting action families (search, quote, negotiation, redemption, partnership). It does not name which sibling tools those actions correspond to, so differentiation from aether_find/aether_offers/aether_offers etc. is only indirect.

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?

"Free" plus an explicit enumeration of message types gives a strong positive-use signal for an open-ended entry point. There is no when-not guidance and no mention of the sibling tools that handle structured operations directly, so an agent must infer that this is the conversational catch-all rather than a scoped alternative.

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