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

Beyond readOnlyHint and openWorldHint, the description discloses two non-obvious behaviors: results are cached server-side by (feedId, rule stamp) so repeat calls are cheap, and image sizes are measured in the background so 'unknown' means not-yet-measured, never passing. The second point is critical, since an agent could otherwise misread 'unknown' as a failure.

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?

Four sentences, front-loaded with the return payload before the imageSizes detail, caching, and usage guidance. The imageSizes sentence is dense but each clause adds distinct semantics (count measured, count below, first ten, remedy); little is wasted.

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 return-value burden and does so for the main issue categories and the imageSizes structure, plus the caching and async-measurement caveats. It stops short of describing the shape of warnings or how to interpret severity, and it says nothing about feedId, but for a one-parameter read tool it is largely sufficient.

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 0% and the single parameter feedId has no description, so the description must carry the meaning. It only references feedId obliquely inside the caching note ('Cached server-side by (feedId, rule stamp)') and never explains what identifier is expected or where to obtain it.

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 opens with a specific verb+resource ('Returns the full validation summary for a feed') and enumerates the contents: missing required fields, format issues such as title length and GTIN format, and warnings. This implicitly separates it from siblings like get_health_summary or get_platform_specs, but no sibling is named, so it falls short of full explicit differentiation.

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 a clear workflow trigger: 'Use this BEFORE writing field/filter rules so you know what to fix,' which ties the tool to a concrete point in the agent's process. It does not state when not to use it or name an alternative for pre-rule inspection, so no exclusions are covered.

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