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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description adds real value by disclosing the 20-item cap, newest-first ordering, and the riskScore scale with direction (0 best). It stops short of describing pagination or error behavior.

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?

Two short sentences, front-loaded with the core operation and results; very little waste. The trailing 'Technical findings, not legal advice' disclaimer is arguably tangential but does set expectations about content.

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 a single optional parameter, the description carries the return-value burden well: it describes ordering, item count, and one key field with its scale. Minor gap is that the remaining per-scan fields and how to use a returned scan id are not mentioned.

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 coverage is 100%: the limit parameter's range (1-20) and default (10) are fully documented in the schema. The description's 'up to 20' merely restates the schema's upper bound and adds no syntax or meaning beyond it, 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?

Names a specific verb+resource (list the most recent scans), scoped to 'the connected account', and adds ordering and result contents (riskScore 0-100, up to 20). This implicitly distinguishes it from per-scan siblings like get_scan_summary or get_scan_status, though it never names an alternative.

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?

The description states what the tool returns but gives no when-to-use guidance, no exclusions, and never routes the agent to a sibling such as get_scan_findings or get_scan_status. Usage is only inferable from the word 'recent'.

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