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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered structurally. The description adds nothing beyond that — no mention of scope, runtime (the wait_timeout_sec parameter hints at async behavior that goes unexplained), or what the audit inspects.

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 short sentence, so there is no waste or burying of information. It is terse to the point of under-specification, but that deficiency is penalized under other dimensions rather than here.

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, no required parameters, and two of three parameters undocumented, the description should carry more weight. As written, an agent cannot tell what the audit covers, how long it runs, or how to interpret top_n.

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?

Three parameters with only 33% schema description coverage; top_n and wait_timeout_sec are undocumented anywhere. The description provides zero parameter guidance, so it fails to compensate for the coverage gap.

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 verb and resource ('Run catalog quality audit'), so the general intent is legible. However, 'quality' is undefined — it doesn't say which checks run (titles, images, attributes, compliance) and does not distinguish itself from siblings like audit_compliance or audit_title_compliance.

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?

There is no guidance on when to run this audit versus the three sibling audit tools, nor on prerequisites, frequency, or what to do with the results. Usage is left entirely to inference.

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