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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial value beyond them: it discloses the return is COMPUTED TEXT rather than a file, that it issues a single RM call regardless of park count, and warns that synthesizing a PDF from the numbers produces an unauthorized document. This is exactly the extra context annotations cannot carry.

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 the DEFAULT designation and the routing rules, and every block (purpose, alternatives, download exclusion, output, args) earns its place. It is longer than strictly minimal – the multiple quoted example queries are somewhat redundant – but the length is justified by genuine routing stakes.

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?

For a four-parameter, read-only analysis tool, the description covers routing, exclusions, output shape (combined Income/Expenses/NOI series, one column per month, park list), and call efficiency, and an output schema exists to carry return detail. Nothing an agent needs to call it correctly 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 0% and all four properties are bare strings with empty defaults, so the description must compensate and does: it gives portfolio ('name or 3-letter prefix'), property_ids (comma-separated), and MM/DD/YYYY formats plus semantic defaults (Jan 1 of current year / today) for the date range. Also explains scoping to a single park via portfolio or property_ids.

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 ('runs the 12-month recap report (ProfitLossRecapMonth, report 45)') and explicitly names itself as the DEFAULT P&L/T12 tool. It distinguishes itself from siblings analyze_financials and analyze_noi by parenthetical contrast, so an agent can route without opening either 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 explicit when-to-use triggers ('show me a P&L', 'T12 for SCE', 'how has NOI moved'), names the two near-sibling alternatives and what distinguishes them, and adds an explicit when-NOT-to-use rule routing download requests to run_report(report_id=45). Nothing is left to inference.

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