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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered without the description. The description adds genuine value by asserting data provenance ("as published," "never from memory"), but it says nothing about not-found behavior, whether an unknown item number errors or returns empty, or any rate/permission constraints.

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?

One front-loaded sentence with the return payload enumerated immediately after the noun phrase. It is dense and the nested colon clause ("and what the descriptor itself says: ...") is slightly run-on, but no sentence 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?

With no output schema, the description correctly spends its budget enumerating returned fields (fees, dates, EMSN cap, flags, exclusions), which is the main thing an agent needs to decide whether this tool answers its question. Only the failure/empty-result case is left unspecified.

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% and the single required parameter is documented with a regex pattern, a range and an example (30445). The description does not mention item_number at all, so it adds nothing beyond the schema, but with full coverage the schema is doing the work and baseline 3 is appropriate.

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 ("Get one MBS item") and then enumerates exactly what the record contains: descriptor, fees and benefits, item type, dates, EMSN cap, assistant/anaesthetic flags, hospital-only, time tier, exclusions. That field list implicitly separates it from get_item_history and get_item_relationships, but no sibling is named, so the differentiation is by inference rather than explicit routing.

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?

There is no explicit when-to-use or when-not statement and no mention of search_mbs_items as the way to discover an item number first. The only guidance-adjacent content is "Every figure comes from the schedule, never from memory," which does tell the agent to call this rather than answer from recall, but that is a trust instruction, not an alternative-selection rule.

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