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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond that: the 100-entry scan limit, the specific detection categories, and the free-vs-paid boundary. It omits anything about output shape or rate limits.

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 tight sentences: what it scans, when to use it, and the paid alternative. Scope is front-loaded and nothing is padded.

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?

For a single-parameter, annotation-backed, read-only scan there is no output schema, so the description should ideally describe the returned issue format; it does not. Still, it covers scope, limits, categories, and the upgrade path, leaving no ambiguity about how to invoke it.

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 a single parameter with 100% schema description coverage, including the maxItems/minItems bounds and the m1, m2 reference convention. The description's "up to 100 entries" merely restates the schema, so the baseline 3 applies.

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 specific verb (scan) and resource (agent memory entries), plus the categories it detects: secrets, personal data, and exact duplicates. It also clearly demarcates itself from the paid Memory Health Check, so the agent can tell the tiers apart.

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?

Gives a concrete condition ("Use when an agent stores long-term memory") and names the alternative (paid Memory Health Check, 0.05 USDC) with what it adds. It does not state when NOT to use this tool or the tradeoff of the 100-entry cap, so the guidance is clear but not exhaustive.

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