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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real context the annotations cannot: the data is point-in-time, checked for look-ahead bias, and includes what the model does NOT catch. It says nothing about response size, latency, or format, but for a static read-only dataset that is minor.

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-loading is good — the point-in-time backtest frame leads — but the body is a single ~110-word run-on sentence with a long comma-separated inventory. The detail is useful, yet the structure costs readability and a bulleted breakdown would have served better.

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?

With no output schema and no parameters, the description must describe what comes back, and it does so thoroughly (16 crises, 3 recessions, 4 market tops, false-alarm rates, per-year summaries, known blind spots). Only the shape/format of the returned data is left unspecified.

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?

The tool takes zero parameters, so there are no argument semantics for the description to carry. Baseline 4 applies; the description spends its words on output content rather than inventing parameter guidance.

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 first clause states a specific verb and resource: how Isoba behaved when back-tested point-in-time over every working day since 1990, with an explicit enumeration of what the record contains (crises, recessions, tops, false alarms, per-year stats). It is clearly a historical-validation resource rather than a live-read tool. It never explicitly distinguishes itself from the sibling get_monthly_history, whose yearly/monthly history overlaps conceptually, so it stops short of a 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?

"Call it before claiming reliability" gives a concrete condition for using this tool, implying when to consult it versus live readings. There are no explicit exclusions and no sibling named as the alternative, so the routing is clear but not fully specified.

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