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

Annotations already declare readOnlyHint/destructiveHint=false, yet the description still adds the 500-id batch ceiling and the important freshness caveat that recorded rule versions can lag current rule wording. It also defines the semantics of empty rule id/code. Return-shape detail is deferred to the output schema, which is appropriate.

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?

Front-loaded with the core purpose, then a compact gloss of the origin codes and rule fields, then the alternative-tool pointer. The long middle sentence is dense but each clause explains a distinct response field; little is wasted.

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 two-parameter read tool with an output schema and safety annotations, the description covers the interpretive burden (origin-code meanings, inheritance vs. override, rule version drift) that structured fields cannot. Only company scoping and pagination-adjacent behavior go unstated, both minor here.

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 only 50% (both params are bare UUID wrappers), but the description compensates by explaining that transactionIds are per-transaction lookups and capping the batch at 500 ids, matching the schema's maxItems. companyId scoping is left implicit.

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 — explaining how each transaction was booked — and enumerates exactly what comes back (account, category, inheritance source, writer origin, rule id/version/code). This is clearly separable from siblings like transaction_get_transaction or accounting_get_journal_entry_by_transaction.

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?

Explicitly routes the agent to transaction_get_categorization_rule to inspect rule conditions, and explains that the rule's current wording may be newer than the version recorded here — a real usage caveat. It does not, however, contrast itself with transaction_get_transaction or the journal-entry tools, so the when-not side is only partially covered.

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