Compare two scans

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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds meaningful non-obvious context about the returned result: it computes a score delta and classifies findings into resolved, remaining, and new. With no output schema, this return-shape disclosure carries real weight, though it omits error/edge behavior for mismatched or missing scans.

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 front-loaded sentence with a colon-delimited enumeration of the diff components. Zero filler, and the core purpose is stated before the detail.

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 low-complexity read-only comparison tool, the description covers purpose and output categories, which is close to sufficient. Gaps remain: no statement of prerequisites (both scans must exist, plausibly from the same project), no behavior when the scans are unrelated or an id is invalid, and no routing guidance against the report/scan siblings.

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 only 33% (only `lang` is documented), so the description must compensate. The before/after framing maps onto `before_id`/`after_id` and confirms ordering semantics (which scan is the baseline), but it adds little beyond what the parameter names already convey and says nothing about id format or same-project requirements.

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?

Clear specific verb+resource ('Compare two scans') plus an enumeration of what the diff contains (score change, resolved, remaining, new). It never distinguishes itself from siblings like slop_report (single-scan report) or slop_scan, so an agent must infer the difference from the name alone.

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?

Usage is implied by the before/after framing — compare an earlier scan with a later one after fixes. However, there is no explicit when-to-use guidance, no stated prerequisite that both scan ids must exist (and presumably belong to the same project), and no routing to alternatives such as slop_report when only one scan is of interest.

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