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

With strong annotations (readOnlyHint, idempotentHint, non-destructive) already covering the safety profile, the description adds genuinely valuable interpretation context: the clarification that 'coverage: complete_for_scope' refers only to the DECLARED SCOPE, never to completeness of legal research, directly corrects a likely misreading. The citation directive (cite the manifest URL, not this tool) also adds behavioral guidance beyond the annotations.

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 description is dense but not padded; every clause earns its place — the handle list, manifest fields, follow-up lookup instructions, the citation rule, and the crucial coverage clarification. It opens with the most important information (what comes back). The first sentence is a long verb-less fragment, which slightly hurts readability, but no sentence is wasted.

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 one-parameter retrieval tool with an output schema, strong annotations, and detailed payload/citation/coverage guidance, the description is largely complete. The main gap is the unaddressed relationship to the sibling get_ingestion_request — an agent gets no guidance about whether to consult request status separately or whether results fail if ingestion is still running. Minor gaps against an otherwise thorough description.

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 100% — the single parameter request_id is fully described as 'The request_id request_ingestion returned.' The description adds nothing about request_id's semantics, but per the high-coverage baseline, a 3 is appropriate since the schema already does the heavy lifting.

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 description never uses an explicit verb like 'returns' or 'retrieves', but the title ('What an ingestion request produced') plus the detailed enumeration of contents (handles, manifest, expectation results) makes the purpose clear. It also differentiates from siblings by listing unique payload elements (expression id, work ELI, manifest fields) that get_ingestion_request or request_ingestion would not produce.

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 guidance is implied rather than explicit: 'Repeat your original lookup with the handles' and 'Pass expressionId as the exact expression query parameter' tell the agent what to do after retrieving results, and the citation instruction is clear. However, the description never names alternatives or states when to use this tool versus get_ingestion_request, so the when-to-use-vs-siblings guidance is absent.

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