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

Annotations already carry idempotentHint=true and destructiveHint=false, so the safety profile is declared. The description adds non-redundant behavioral context: it writes a durable user override that AI enrichment will not overwrite, and the journal entry re-derives from the account. This goes beyond the annotations in a meaningful way.

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 sentences, each earning its place: action with examples, differentiation from a sibling, and the persistent-override behavioral caveat. The content is front-loaded with the core action and no filler.

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?

With an output schema present and annotations covering idempotency/safety, the description covers target, preferred usage, behavioral side effects, and where to source valid inputs. It does not describe failure behavior for invalid paths or the optionality of glAccountPath, but that is a modest gap for a write tool of this complexity.

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-level descriptions are near-useless ('UUID value wrapper') and glAccountPath has no description in the schema, but the tool description materially enriches glAccountPath with full-path semantics and examples such as 'expenses/software-and-subscriptions'. A minor miss: glAccountPath is not marked required in the schema, and the description does not clarify that oddity.

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 pinpoints a specific verb and resource ('Book a transaction to a chart-of-accounts account') and gives unambiguous examples of the account path format. It also explicitly distinguishes this tool from its sibling, transaction_categorize_transaction, so an agent can tell them apart without inspecting either 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 an explicit selection rule ('prefer it over transaction_categorize_transaction') and tells the agent where to find valid inputs (accounting_get_chart_of_accounts). However, it does not address the near-named batch variants (transaction_batch_categorize_transactions_by_account), so the when-not-to-use guidance for scale is incomplete.

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