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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the bar is lower. The description adds the partial-update behavior (omitted fields preserved) and a required user-confirmation workflow, though it does not spell out what a direction/category change destroys or how failures surface.

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?

Four sentences, front-loaded with the purpose, then prerequisite, then the partial-update rule, then the confirmation requirement. No filler; each sentence carries a distinct instruction.

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 12-param destructive mutation with annotations but no output schema, the description covers purpose, prerequisite lookup, partial-update semantics, and a safety confirmation step. It stops short of describing error/rollback behavior or the direction-change cascade, leaving minor gaps.

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 baseline is 3, but the description adds a rule the schema does not encode: this is a PARTIAL update where omitted fields are left as-is, and transaction_id must accompany only the changed fields. That meaningfully changes how an agent fills the 12-property payload beyond the per-field schema text.

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 (correct/update) and resource (ledger transaction) and enumerates the correctable fields (amount, date, category, payee, who paid, heir/asset). It explicitly distinguishes itself from creating a new correcting entry, so an agent can separate it from log_transaction without inspecting schemas.

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 prerequisite ('Find the transaction's ID with get_transactions first'), names the alternative it is not ('Use this (not a new correcting entry)'), and adds a confirmation step before calling. When-to-use is tied to the user-facing trigger ('the user says an amount or detail was wrong').

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