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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description enriches this substantially: it states the tool returns a live quote and the exact unsigned transaction, that relayers handle every subsequent hop after broadcast, that no confirm step is required, that nothing is held by this server, and that fees are free. It also discloses failure-mode behavior by encoding refusals, which goes well beyond the bare annotation flags.

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 dense but front-loads the core purpose in the first sentence, then packs route limitations, fee structure, and failure-mode behavior into subsequent sentences. It is longer than typical, but every clause carries operational information an agent needs; the structure is logical and not padded.

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?

For a complex multi-chain bridge preparation with an output schema present, the description covers all necessary contextual pieces: supported routes, the Osmosis exclusion and prerequisite, the non-custodial signing model, the lack of a confirm step, cost/fee expectations, and the minimum recommended amount. Nothing an agent needs to decide whether and how to invoke this tool is missing.

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 the baseline is 3; the description adds meaning on top by explaining the practical implications of amount (flat toll ~333 REGEN, so send at least ~2,500 REGEN and batch), by reinforcing that sender and destination must be the caller's own addresses, and by noting the 6-decimal unit is consistent across chains. This is genuinely useful beyond the schema property descriptions.

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 opens with a specific verb-resource pair—'Prepare a REGEN bridge transaction'—and immediately distinguishes it from a raw transfer: it is non-custodial, caller-signed, and returns an unsigned transaction. It further narrows scope by listing exact supported routes (regen→arbitrum, regen→base, base→regen), making it unambiguous among the many sibling 'prepare_*' tools.

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 description clearly indicates when to use the tool: to bridge REGEN between the three named chains in a single self-signed transaction, and it explicitly excludes Osmosis-originating REGEN unless first IBC-transferred back. It also gives actionable guidance on minimum amount and batching due to the flat toll. However, it does not explicitly contrast with other preparation tools, relying instead on the resource-specific subject to differentiate.

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