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

Annotations only cover safety (readOnly/idempotent/non-destructive); the description adds substantive behavior: per-company fiscal calendars so each row carries its own period and dates, decimals-friendly units (actual dollars, per ADS, split-adjusted shares), FX conversion at the rate recorded per period, and the important non-failure contract that a company missing the figure or period gets an explanatory row instead of an error.

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?

Purpose and the 2-10 scope are front-loaded before the period and unit details. It's a dense multi-sentence block rather than a bulleted structure, but each sentence carries distinct information (defaults, period syntax pointer, missing-data behavior, units).

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?

There is no output schema, so the description must carry the return contract, and it does: rows state their own period, dates, and source field; units and currency treatment are spelled out; and missing data is described as a row rather than an error. Nothing an agent needs to call or interpret the result is missing.

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, but the description adds real meaning: it resolves what the schema's bare 'latest' default actually means (latest discrete period, quarter or newer fiscal year), explains that periods differ per company, and confirms the 2-10 ticker bound in prose.

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 (compare) plus the resource (2-10 companies) and the exact scope: one standard figure at a time. An agent can immediately tell this is the multi-company view rather than the single-company get_figure, and the figure vocabulary is anchored to a named sibling.

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 clear operating context: it defaults to each company's latest discrete period, lists the period strings that select alternate windows, and routes figure naming to get_figure. It does not explicitly say 'use this instead of get_figure when comparing several companies,' which leaves the sibling boundary to inference.

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