reports_followup

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

The description adds meaningful context beyond the annotations: it states that no source excerpts, rescans, network, or device actions occur, warns that 'Disappearance never proves remediation', and explains hash-binding and portable_inputs restrictions. These are useful behavioral boundaries not captured by readOnlyHint or idempotentHint. Some phrasing ('retain comparison blockers') remains opaque.

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?

The purpose is front-loaded in the first sentence, and the description is not bloated. However, several sentences are dense with unexplained domain jargon, and the portable_inputs sentence is particularly opaque, making the description harder to parse than its length suggests.

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?

An output schema exists, so return values need not be explained. The description covers important caveats and non-actions, but with 4 parameters and 0% schema coverage it leaves the input semantics almost entirely unclear. For a follow-up analysis tool, an agent still lacks enough information to know what to pass for before and after.

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 0% and the description only mentions portable_inputs, in a cryptic sentence about 'identical-complete-source relocation rule'. The required parameters before, after, and finding_id are never explained—an agent cannot tell whether before/after are report hashes, IDs, or paths. The description does not compensate for the schema 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?

The first sentence states a specific verb and resource: 'Follow one original finding across immutable reports.' It is reasonably clear that this is a cross-report finding-tracking tool, though the surrounding jargon ('possible continuations', 'comparison blockers') adds ambiguity. It does not explicitly distinguish itself from siblings like reports_compare or verify_finding.

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 opening sentence—use when tracking one finding across reports—but there is no explicit when-to-use guidance, no named alternatives, and no exclusions beyond 'No source excerpts, rescans, network or device actions.' An agent must infer when this tool is preferable to reports_compare or verify_finding.

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