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

Annotations already establish readOnly/non-destructive, so the bar is lower, yet the description adds real behavioral context: it enumerates the event types the log can contain, describes each entry's payload (signed quantity, resulting on-hand, outlet, employee), and — most valuably — explains that only applied changes appear, so an empty log on an untracked line is itself the answer. That is non-obvious behavior an agent could not infer from annotations.

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 scope and ordering, then use cases, then payload shape, then the empty-log caveat — a sensible progression. It runs four sentences and includes a long action-name enumeration that is somewhat list-heavy, but each sentence carries distinct information.

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?

There is no output schema, so the description correctly compensates by describing entry contents and the ordering. Filter parameters remain unexplained, but the schema documents them at full coverage. For a read-only history tool this is close to complete.

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 100%, so baseline is 3. The description implicitly surfaces the action vocabulary (SALE, DAMAGE, THEFT, ...) that the `actions` filter accepts, but it says nothing about the action/outlet/date-range filters, their pairing rule (startDate with endDate or neither), or what 'newest first' means for ordering control.

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 scoped precisely ('Every recorded stock movement for ONE product, newest first') and frames it as 'the audit trail behind a count', which cleanly separates it from hub_get_stock (current on-hand) and hub_export_stock_csv (bulk export). An agent can pick it out of ~130 siblings without opening the 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?

Gives an explicit use case — 'Use this when the merchant disputes a number: state what the log shows rather than guessing at a cause' — which is genuine when-to-use guidance. It does not name an alternative sibling (e.g. hub_get_stock) for the 'what is the number now' case, so the routing is clear but not exhaustive.

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