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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world); the description adds real operational context beyond that: default 3-year window, ranking by absolute total, per-Location output labelling, and the fact that unreachable Locations are reported as skipped rather than failing the call. It does not address result sizing or how top_n bounds the matrix, which is the one material behavioral gap.

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-loads the identity, output shape, and the queries it answers in the first three blocks, with alternative routing before the parameter detail. The location paragraph is longer than the rest but every clause (comma list, "all", blank fallback, skipped Locations, IDs scoped to one Location) is decision-relevant, so little is wasted.

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?

An output schema exists, so return values needn't be spelled out, and the routing plus location semantics are solid. However, for a 6-parameter, zero-coverage-schema tool, leaving top_n, portfolio, and property_ids entirely undefined means an agent cannot confidently scope the analysis to a portfolio or set of properties from this description alone.

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 0%, so the description carries the full burden, but it only explains `location` (thoroughly: single ID, comma list, "all", blank behavior, per-Location caveat). The other five parameters — top_n, portfolio, property_ids, start_date, end_date — get no treatment; start/end are only implicitly referenced as 'date range' and 'no dates given', and top_n's ranking/truncation role is never stated despite the 'ranked by absolute total' claim.

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?

Names a specific verb and resource ('Multi-year P&L by account') and pins it to a concrete artifact (ProfitLossRecapYear, report 201). The 'Year-matrix per account across the requested date range, ranked by absolute total' line describes the output shape, and the explicit contrast with analyze_pl_yoy and analyze_pl_trend makes it unambiguous against its closest siblings.

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 routing rules: use analyze_pl_yoy for year-over-year deltas, analyze_pl_trend for monthly trajectory, and this tool for multi-year trajectory. It also enumerates the natural-language questions it answers and states the default 3-year window when no dates are supplied, so the agent knows both when to pick it and how to call it with no arguments.

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