Screen symbols or sectors by news attention

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), so the description's job is supplementary — and it delivers: it enumerates the returned row fields (mentions, topics, sources, sentiment counts, score, change) and warns that omitting entity_kinds mixes companies with rates, commodities and central banks. This is meaningful behavioral context beyond the annotations.

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 the purpose and a quotable use case before diving into parameter nuance. Dense but largely waste-free; the parameter detail could be tightened marginally, and the second sentence is a slightly redundant gloss on the first.

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 7-parameter filtering tool with no output schema, the description anticipates the important gaps: it lists the row fields that will be returned, explains the period windows, and flags the entity_kinds default mixing behavior. Only minor omissions remain (e.g. what 'score' represents, limit interaction).

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 71%, and the description compensates for the gaps well: it documents the full entity_kinds vocabulary (equity, etf, index, rate, fx, crypto, commodity, org, private, country) that the schema only shows as a bare string, states that sector applies only when rank=symbols, and explains the sort=change incompatibility with period=window. These are cross-parameter constraints the schema cannot express.

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 precise verb+resource: "Rank symbols (or the 11 GICS sectors) by news attention," and adds a concrete use case ("which tickers are suddenly in the news"). It is clearly distinguished from siblings like get_topic or sentiment_series, though the relationship to the closest sibling `trending` is left implicit.

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 context for when to reach for it (sudden news attention on tickers) and conditional guidance — sort=change is unavailable for period=window, and entity_kinds should be set to "equity,etf" for tradable tickers. No explicit when-not or named-alternative routing to siblings, so it stops short of a 5.

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