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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower; the description earns credit by disclosing the no-look-ahead guarantee, which is a genuine behavioral trait not encoded anywhere in the schema or annotations. It does not say what data classes (income statement, ratios, etc.) come back, which is the remaining 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?

Two short sentences, zero filler, with the point-in-time constraint front-loaded before the default. Every clause earns its place.

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 2-parameter read tool with no output schema, the PIT semantics and the default are covered, but the description never indicates what "fundamentals" actually contains. With no output schema to fall back on, an agent cannot predict the return shape.

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?

Coverage is 50%: as_of is fully documented in the schema and the description only restates its default, while symbol has no schema description and the description adds nothing beyond "one symbol." Baseline 3 is appropriate since the schema carries most of the weight.

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 ("Returns fundamentals for one symbol") and pins the temporal semantics with "as known on as_of (no restatements from the future)." It is clearly distinct from siblings like get_bars or get_macro_vintage, though it never explicitly routes against an alternative.

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?

"as_of defaults to today" implies the usage context (point-in-time, backtest-safe lookups) but never states when to choose this tool over a sibling or when a caller would want a non-default as_of. Usage is implied rather than guided.

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