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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by specifying that the tool only returns counts and does not fetch rows, which prevents agents from expecting detailed transaction data. It also clarifies the grouping (pending/posted/excluded), beyond what annotations provide.

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?

The description is two sentences, with the core action and scope front-loaded in the first sentence and the use case in the second. There is no wasted wording, filler, or repetition of the tool name, making it highly efficient.

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?

The tool is low-risk (read-only), has a single well-described parameter, and has an output schema, so the description need not explain return values. The stated grouping and 'without fetching rows' fully capture the relevant behavior, and the use case informs the agent what the counts are for. Nothing essential for correct invocation is missing.

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% for the single parameter, and the schema describes companyId as a UUID value wrapper. The description adds no extra semantic detail about companyId, which is acceptable because the schema already fully documents the required input. This matches the baseline for high schema coverage.

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?

The description uses a specific verb ('Count') and resource ('bank transactions per bookkeeping review tab'), names the three statuses (pending, posted, excluded), and explicitly notes that it does this 'without fetching rows.' This distinguishes it from row-returning siblings like accounting_get_list_review_items, so an agent can identify it correctly without opening schemas.

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?

The description states a clear usage context ('Use to report how much review work is outstanding') and implies an alternative by saying 'without fetching rows.' However, it does not explicitly name the alternative tool or state when not to use it, so it stops short of full when/when-not guidance.

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