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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds ordering semantics (worst first), default-state behavior, the resolved-then-refound-is-open rule, the omission of evidence, and an explicit prompt-injection warning about untrusted scanned-site text.

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?

Dense but front-loaded: purpose first, then state/filter/identity/trust notes. Each sentence adds value, though the parenthetical offset tip partially repeats the schema.

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?

No output schema exists, so the description must characterize returns; it names findingId and fingerprintHash and notes evidence is excluded. It stops short of enumerating all finding fields but covers the agent-critical traits.

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%, so the baseline is 3. The description adds nuance beyond the schema: severity ordering, nextOffset-to-offset round-tripping, and the resolved-refound interpretation that the schema's 'closed findings' wording only hints at.

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 (List), resource (a completed scan's findings), plus ordering (worst first) and pagination mode. Clearly distinguishable from sibling get_finding (single item) and get_scan.

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 clear context: findings of a completed scan, filtered by category and state, paged via nextOffset. It does not explicitly name sibling alternatives such as get_finding for a single result, so routing is only implicit.

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