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

Annotations already declare readOnlyHint=true, destructiveHint=false, so safety needs no restatement. The description adds the grouping semantics and endpoint path, but says nothing about pagination behavior or how the grouped rows are shaped, which matters for a summary call.

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 dense sentence carries the aggregation definition, then the alternative mode, then the example question. No filler, and the core purpose is front-loaded.

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?

No output schema exists, and the description does name the returned measures (net, tax, total, count), which is the key missing piece for an agent. Coverage is only slightly short on response shape per grouping and pagination, both partly handled by schema fields.

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%, so limit/offset/code_sii/emitted_from/emitted_to are fully documented there. The description's only parameter gloss ('set per_document to list each document instead') largely restates the schema's own wording, so it adds little beyond the baseline.

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 concrete verb and resource ('Totals of sales documents') plus the exact aggregation dimensions (net, tax, total, count; by month, document type, office). Clearly distinguished from bsale_list_documents by the aggregation framing and the per_document escape hatch.

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 ('how much did we sell in September?') and the condition for the alternative shape (set per_document to list each document instead). It does not mention the closest sibling, bsale_user_sales_summary, which is the main remaining routing ambiguity.

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