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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is low. The description still adds real behavioral context beyond them: the null value for brands with no mentions in a bucket, plus the top_n default (20) and cap (50).

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 dense sentences, zero filler, with the metric and scope front-loaded before the fallback rules and the null edge case. Every sentence earns its place.

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 must describe the return: it gives the metric's unit range and the per-bucket null convention. It omits the required interval granularity and the overall list-of-series shape, minor gaps against a 100%-covered schema and full annotations.

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 adds the interaction semantics the schema lacks: how brand_id, segments, and top_n compete as scoping mechanisms and which wins when unset. It does not add detail on tags/monitors/countries/platforms, which the schema already covers.

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 precise metric and scope: 'Average sentiment score (0-100) of each tracked brand's mentions per bucket.' The verb/resource (sentiment per bucket) inherently distinguishes it from the position, share-of-voice, and visibility time-series siblings, so an agent can select it without opening the 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?

Explicitly defines the three scoping modes: brand_id for a single line, segments for a segment's brands, otherwise top_n by mention count. This tells the agent how to drive the tool, though it names no alternative tool and gives no when-not guidance.

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