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

readOnlyHint=true already establishes this is a safe, non-mutating read, so the description does not need to restate safety. It adds the grouping dimension and the REST endpoint, but says nothing about auth requirements, rate limits, or what the totals actually contain (net, tax-inclusive, currency). Modest added value on top of 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?

Two sentences, front-loaded with what the report returns, followed by the endpoint. Zero filler. The endpoint sentence is the weakest element since it adds little for an agent choosing a tool, but it costs almost nothing.

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 is the only place the return shape could be described, yet it never states the fields or structure of the returned totals or how totals are aggregated. Schema coverage is complete for inputs, so the gap is confined to output expectations.

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%: start_date/end_date formats, max_results default and cap, and report_type values 1-4 are all documented in the schema. The description's grouping list merely restates report_type, adding no new meaning. Baseline 3 applies.

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 resource and scope: 'Purchase totals for a period, grouped by invoice, vendor, item or fixed asset.' That is a clear verb-free but identifiable report operation, and 'purchase' inherently separates it from merit_sales_report and merit_customer_debts_report. It stops short of naming any sibling explicitly, so it is clear but not differentiated in-text.

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 when-to-use guidance, no prerequisites, and no routing to alternatives such as merit_list_purchase_invoices or merit_get_purchase_invoice for a single invoice. The only usage signal is the implied 'report' framing, which the agent must infer.

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