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 profile is covered. The description still earns credit by adding that it will not re-score or trigger a re-fetch, and by enumerating the three things it reports (ages, latest re-check, stalest picks). It omits how many items come back and whether results are ordered.

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?

A single dense sentence with the payload front-loaded and the key exclusion ('Never re-scores') placed last for emphasis. It is tight, though the stacking of Depot-specific jargon (ageDays, staleAfterDays, Depot Picks) makes it slightly hard to parse on first read.

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 and no parameter documentation, the description has to carry the return shape, which it does partially by listing what is reported. The gaps are the `limit` semantics and the absence of any cue about ordering or defaults. Adequate to call correctly, but not complete.

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?

There is one parameter, `limit` (1-198), and the schema provides zero description coverage for it. The description mentions 'stalest Depot Picks' but never explains that `limit` controls how many of those picks are returned, nor what happens when it is omitted. With no schema text to fall back on, this gap is left entirely unaddressed.

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 names the specific resource (Depot's scores, prices, free rows, source re-check timestamps, stalest Picks) and frames it around ageDays vs staleAfterDays, which is more concrete than the bare name 'freshness'. It also states the negative ('Never re-scores'), which separates it from tools like check or changes. It stops short of a clean verb+object framing, but an agent can tell what it gets back.

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?

'Never re-scores' implies this is a diagnostic/inspection call rather than a verification or refresh, which is useful inference. However, no sibling is named and there is no explicit condition for choosing this over coverage, check, or changes, so the agent must infer when staleness reporting is the right call.

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