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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds one genuine domain rule — 'Input values are never sources for results' — which clarifies provenance semantics, but says nothing about result volume, pagination, or whether unprocessed rows appear.

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 tight sentences with the core behavior front-loaded and no filler. The second sentence earns its place by stating a non-obvious provenance rule, though the first sentence could be slightly plainer about the row/result pairing.

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, the description must convey what comes back, and it does so only at a high level ('results ... and their sources'). For a single-parameter read-only tool that is borderline adequate, but the missing batch_id meaning and result shape leave real gaps.

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 description coverage is 0%: batch_id is documented only as a non-empty string with no explanation. The description never mentions batch_id at all, so it fails to compensate for the coverage gap — an agent cannot tell whether it needs an investigation batch id or a different batch identifier.

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 ('Reads') and a specific resource (each input row paired with the results it produced and their sources). This is meaningfully distinct from siblings like get_investigation_inputs and get_research_rule_results, though it never explicitly says so.

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?

No guidance on when to call this versus get_investigation_inputs, get_investigation_batch, or get_research_rule_results, and no prerequisites such as a batch needing to be completed first. The agent must infer that this is the per-row results reader.

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