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

Beyond the annotations, the description discloses that it returns unsigned transactions for the wallet to sign, that it is 'simulated from the wallet', and that the take direction can be blocked when the desk is paused – all of which are non-obvious operational facts. The readOnlyHint=true is not contradicted because the tool builds but does not submit transactions, though the description could say more explicitly that nothing is broadcast until the caller signs.

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?

Two sentences, front-loaded with what is returned (unsigned transactions) and then the constraints; there is no filler. It is dense but each clause 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?

For a 3-parameter prepare tool with no output schema, saying it returns unsigned transactions is the essential return-value disclosure, and the collateral-limit and paused-desk conditions cover the main failure modes. It omits what happens if both `add` and `take` are supplied at once, which is the one real ambiguity left.

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 100%, so both `add` and `take` are already documented in the schema, including the "all" sentinel for `take`. The description maps each direction to its parameter, which is mildly useful, but adds no new syntax or constraints beyond what the schema states.

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 concrete verb and resource: builds unsigned transactions that add USDG to (or take back from) the collateral held against a gAIX short, and it separates the two directions via the `add` and `take` parameters. It stops short of naming its closest relatives (gaix_withdraw, gaix_short_close, gaix_short_open), so an agent still has to infer why 'take' differs from a plain withdraw.

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?

'With a short open, what stays held keeps it under three quarters of its limit, and taking back waits while the desk is paused' gives real context: a precondition (short must be open), a constraint on how much can be added, and a blocking condition for taking back. What it lacks is routing guidance to alternatives such as gaix_withdraw or gaix_short_close when the user wants to exit rather than top up.

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