News volume and sentiment over time

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it documents the omitted empty buckets, and warns that unless `until` is set the series ends on a still-incomplete day/hour so a low last bucket must not be read as a drop. That is precisely the kind of interpretive gotcha an agent would otherwise misread as data.

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 scoping rule are front-loaded in the first sentence, followed by the return-bucket contract and then the last-bucket caveat. The bucket specification sentence is dense with seven field names and a formula in one breath, but nearly every clause carries information, so the length is defensible.

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 no output schema, the description carries the full burden and meets it: it defines each bucket field, the score formula, source counting, empty-bucket omission, and time-range defaults. An agent can both call the tool correctly and interpret its results from this text alone.

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 86%, so the baseline is 3, but the description adds a cross-parameter constraint the schema cannot express: the four entity parameters are all optional and nullable in the schema, yet the description imposes 'exactly one of' and specifies the interval default windows. That is genuine semantic value above the field descriptions.

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?

The first line states a specific resource (news volume and sentiment), a specific shape (over time), and an exact scoping rule (one of symbol, sector, theme_id or topic_id). That is enough to separate it from siblings like search_statements, trending and themes without opening a 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?

It gives concrete selection guidance: pick exactly one entity dimension, and interval=hour is bounded to 14 days (default 7) while interval=day covers the whole window. It never names a sibling tool or states when to prefer `trending` or `search_statements` over this one, so the 'vs alternatives' half of the bar is unmet.

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