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

Beyond annotations, it explains period definitions, output contents (income/expense/NOI/net-income deltas, percentages, totals, top movers), and multi-location behavior including skipped locations. That is substantial behavioral context not covered by the readOnly/idempotent hints.

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 purpose and period semantics are front-loaded, and the example questions earn their place. The structure is slightly imbalanced because a full paragraph is spent on location while the other parameters are unaddressed, but there is little outright filler.

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 output schema and rich annotations reduce the burden, and the description covers what the report returns and how locations behave. Still, for a six-parameter analysis tool with no schema descriptions, the missing semantics for portfolio, property_ids, top_movers, and dates leave material gaps for correct invocation.

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?

Only location is meaningfully described (ID, comma list, 'all', blank default, per-location labeling); the other five parameters—start_date, end_date, portfolio, top_movers, property_ids—get no semantic explanation despite 0% schema description coverage. The description therefore leaves most filter parameters to inference.

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 gives a specific verb and resource ('Year-over-year P&L comparison') and names the underlying report (ProfitLossComparePreviousYear, 144), plus period semantics. It does not explicitly distinguish this from nearby siblings like analyze_pl_trend or analyze_pl_multi_year, so it falls short of 5.

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?

It supplies concrete use-case questions ('how's NOI tracking vs last year', 'what's driving income growth', etc.) that make the intended context clear. It lacks explicit when-not guidance or named alternatives, so no 5.

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