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

Annotations already establish this as a safe, idempotent read, so the bar is lower; the description nonetheless adds substantive behavioral context: data is delayed, values are privacy-thresholded, suppressed or unobserved buckets appear as missing rather than zero, and counts are rounded researcher-hours rather than people or recommendations. Those caveats meaningfully change how an agent interprets a result set. It stops short of describing freshness lag magnitude or update cadence.

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?

No sentence is wasted and the defining property (delayed, privacy-thresholded, contributor-sourced) is front-loaded. However, the remaining content is a dense comma-separated enumeration of seven data facets in a single block, which is harder to scan than a short structured list and blurs what a default call actually returns.

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 burden of conveying return content and does so by naming the sections returned (most researched tickers, abnormal attention, country/sector totals, price/volume context, news, history) plus the suppression rule for absent data. Remaining gaps are response shape and pagination behavior under `limit`.

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 description coverage is only 33% — only `symbol` is documented — yet the description says nothing about `limit` (max 100, default 20), `window` (now/today/week), or that results can be scoped to a single symbol. With the schema underspecified, the description should have compensated and does not; the `window` enum has no semantics for how 'now' differs from 'today'.

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 description states a specific resource (delayed, privacy-thresholded research attention from contributing Gloom users) and enumerates the content dimensions it covers. It is clearly a read/aggregate feed, distinguishable from data-heavy siblings like market.quotes or market.history. It lacks an explicit verb and does not name the closest alternative (apps.attention), so sibling differentiation is implied rather than stated.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite apps.attention and market.history appearing to overlap. The agent must infer the tool's role from the content enumeration alone.

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