get_historical_prices

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

Annotations already establish the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the description is not obligated to restate them. It adds genuinely non-obvious behavior instead: default output is a truncated Markdown view, full series only via response_format='json', and unsupported period/interval pairs return a short message rather than an error. It does not mention rate limits or data-source latency, which keeps it off a 5.

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?

Three short paragraphs ordered by importance: what it returns, when to use it versus alternatives, then output/edge-case mechanics. Every sentence carries distinct information, and the parenthetical example is anchored rather than decorative.

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 data tool with full schema coverage and an output schema, everything an agent needs to call it correctly is present: default behavior, format switch, interval/period compatibility, and truncation risk. The return-value detail is arguably redundant given the output schema, but it costs nothing and resolves ambiguity about default truncation.

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 100%, so the baseline is 3; the description nonetheless adds real meaning by explaining the semantic effect of response_format (markdown = summary stats plus last 10 rows vs json = full series) and by tying interval choice to period length. It does not expand the period/interval enums beyond the schema's own examples, so it stops short of a 5.

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?

Opens with a specific verb+resource combination: 'Historical OHLCV price series for one stock over a chosen period/interval', and immediately enumerates the included derivatives (summary stats, total return). It also explicitly names the two sibling tools it is not (get_stock_quote for current price, get_dividends_splits for corporate actions), so an agent can disambiguate without opening any 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 an explicit when-to-use framing ('how has X done over the last year') plus named alternatives with the exact condition that selects them: single current price -> get_stock_quote, dividend/split events -> get_dividends_splits. It further constrains usage with a practical caveat that intraday intervals only work for short recent periods and long periods may truncate.

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