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

Annotations already declare a safe read (readOnlyHint, idempotentHint, destructiveHint=false), so the description needn't argue safety and instead adds genuinely non-obvious behavior: ambiguity handling via `entity.candidates`, provenance citation requirements, `derived: true` on US Q4, Nordic PDF-vs-market-data `data_quality_warnings`, and the reported/computed ratio `basis` rule. The one substantive gap is the `latest_period.available = false` path, where it tells the agent what to say but not the fuller recovery procedure beyond `nearest_available`. Strong content, but a few behaviors (e.g. caching, rate limits, whether repeated calls are stable) go unstated.

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 purpose and sibling routing, then a structured Args/Returns breakdown that an agent can scan. It is long, and a few clauses (the chart invocation pattern, the ratio-basis aside) sit in the main description rather than in a narrower section, but nearly every sentence conveys a fact the agent would otherwise have to guess.

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?

Rich across the parameters and the sibling boundary, and the return-shape paragraph is a bonus rather than a necessity given the output schema. What it omits is minor but real: no guidance on call cost or latency for `period_type: "both"` over large quarter counts, and the fiscal-quarter caveat is stated without a concrete example of resolving it beyond checking `period_end`.

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 and does: it documents `years` default/max, `quarters` market-specific defaults and maxima, `market` omission behavior (auto-detect), all four `period_type` enum values including the `by_quarter` side effect, and the interaction where `quarter` 1-4 forces quarterly. It also explains `company` accepts names or tickers with fuzzy matching. This is precisely the compensating detail a 0% coverage schema requires.

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 ('Get key financial figures for one company as a yearly series'), enumerates exactly which figures are returned, names the covered markets, and explicitly routes line-item and multi-company needs to `get_financial_statement` and `compare_companies`. An agent can distinguish it from every close sibling without opening a 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 alternatives and the conditions that select them ('For line items use get_financial_statement; for several companies, compare_companies'), plus when to set `period_type` to each of its four values and when to pin `year`/`quarter`. It also warns that the fiscal period is the company's own, not calendar, which pre-empts a common misuse.

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