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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add context, which it does: it discloses that results include the print and price move, not just transcript text, and warns against fabricated symbols. It does not discuss volume limits or how results are scoped per call, so it falls short of fully rich behavioral disclosure.

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 purpose, then usage, then arguments — the right order. The Args list is long but earns its space given 7% schema coverage. A few sentences are telegraphic to the point of ambiguity ('Do not invent symbols.', 'plus the print') and could be tightened into flowing guidance.

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 14 parameters, an output schema, and full annotations, the definition covers the essentials an agent needs to call it correctly. Remaining holes are combinatorial: what happens if neither tickers nor sector is supplied, and whether date-based and fiscal-based ranges are mutually exclusive, are left implicit, and strategy_id is undocumented.

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 7%, so the description must carry the load, and its Args block does exactly that: date formats (YYYY-MM-DD), season pairing rules (conference_from with conference_to, compare_from with compare_to, fiscal_year with fiscal_quarter), value ranges (1-8, 1-5, quarter 1-4), the default of 3, the 'not used with compare' restriction, and a sector disambiguation ('Banks, insurers, and brokers are Financials'). The gap is strategy_id, which appears in the schema with its own description but is omitted from the Args list entirely.

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 — retrieve what was said on earnings calls, plus the print and the price move — which is more than a restatement of the name. It then explicitly separates itself from finance_search (report dates, Earnings Deep Dive, full transcript), so an agent can route without opening either 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 concrete usage shapes (one season across several names, or this season versus a prior season), the two selection paths (tickers you already have vs. a sector label), and an explicit exclusion routing to the sibling finance_search. The constraint 'Do not invent symbols' and the note that 'Optional when sector is set' also imply the fallback when tickers are absent.

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