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

The description adds substantial traits beyond the annotations: a 7-day recovery window, an explicit carve-out for Plaid-managed transactions, and the fact that it can fail with an error dict. It is consistent with the annotations (readOnlyHint=false for a mutation) and enriches them rather than contradicting them.

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?

Purpose and constraints are front-loaded, and the Args/Returns block is compact. The structured style is slightly mechanical but every line carries information and nothing is 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 single-parameter mutation with no output schema, the description covers what it does, the preconditions, the failure mode, and the return value ('restored transaction details, or an error dict'). Nothing an agent needs to call 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?

Schema description coverage is 0%, so the description must carry the parameter. It does: 'The ID of the soft-deleted transaction to restore' clarifies that the input must reference a soft-deleted record, which meaningfully constrains valid values beyond the bare integer type.

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 ('Restore a soft-deleted transaction') and immediately scopes it against the broader transaction family (manually created, soft-deleted, not Plaid-managed). An agent can distinguish it from delete_transaction/update_transaction without opening any 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?

It gives strong preconditions: only soft-deleted transactions, only ones deleted within the last 7 days, and explicitly not Plaid-managed transactions ('hard-deleted on their original delete'). This is clear when-to-use/when-not context, though it doesn't name the inverse sibling (delete_transaction) as an alternative.

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