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

No annotations are provided, so the description carries the full burden. It usefully discloses a hard invariant (opposite income/expense types) and a null-for-standalone case is implied, but it says nothing about reversibility, required permissions, idempotency, or what the mutation returns on success/failure — meaningful gaps for a write operation with zero annotation coverage.

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 short sentences with the core action front-loaded and the constraint placed before the optional parameter. Nothing is padded, though the parenthetical glosses on originalTxId/refundTxId repeat what the schema already says.

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 three-parameter mutation with no annotations and no output schema, the description covers the core semantics and one invariant but leaves the mutation's side effects, permission requirements, and failure behavior unaddressed. It is adequate, not complete.

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 each parameter is already documented in the schema; the baseline is 3. The description restates which ID is which and adds the split-targeting intent, but does not clarify the schema's 'pass null for a standalone refund' allowance, so it adds little beyond the structured fields.

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 verb and resource ('Mark an existing transaction as a refund of another transaction') and immediately names the two operands, so the agent can distinguish this from link_transfer, link_transaction_to_portfolio, and the inverse unlink_refund without opening the schema.

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?

Gives a domain constraint that governs when the call is valid ('The two transactions must have opposite types (income vs expense)') and notes the optional split targeting, but never says when to use this tool versus unlink_refund or how to handle the case where the types don't match. Usage is implied rather than routed.

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