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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description isn't carrying the safety burden alone; it still adds real value by disclosing the 10-minute expiry and that the call moves no funds. It doesn't say whether a second call within the window returns the same message or a fresh one, which is the one behavioral ambiguity left.

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 tight sentences, front-loaded with the step position and the payoff, then the return shape and constraint, then the next action. Every sentence carries information.

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?

There is no output schema, but the description supplies the return shape ({ message }) plus the signing standard and validity window, which is everything needed for this single-parameter read step. Nothing an agent needs to invoke it correctly 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?

The single wallet parameter has 100% schema coverage including the address pattern and EOA/EIP-1271 note, so the baseline of 3 applies. The description's only wallet reference ('your wallet must sign') adds no constraint beyond the schema.

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?

States a specific action and artifact: step 1 of 2 to obtain an API key, returning the exact text to be signed with personal_sign (EIP-191). It is clearly distinguishable from the sibling trnch_register, which is explicitly labeled as step 2.

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?

Explicit sequencing is given: call this first, then call trnch_register with the resulting signature. 'No browser' frames the alternative flow, so an agent knows this is the headless path rather than the interactive one.

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