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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety bar is covered. The description adds real value beyond them: it explains the status taxonomy that separates never-published gaps from paywalled ones from unworked ones. It does not describe the response envelope or ordering, though pagination is handled by the schema.

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?

Three short sentences with no filler; the purpose and the pre-conclusion trigger are front-loaded. The status taxonomy is compressed into a single parallel clause that reads well. Slightly cryptic phrasing in sentence two costs a point but nothing 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?

A four-parameter, no-output-schema read tool needs its description to carry the return shape and key parameter meanings. The gap/status model is well conveyed, but the ambiguity of `q` and the absence of any statement about the result envelope (beyond what `limit` describes) leave an agent guessing before invocation.

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?

At 50% schema coverage the description must compensate. It does add genuine meaning to the bare `status: string` parameter by explaining what the status categories represent. However, `q` is entirely unaddressed — an agent cannot tell whether it is a record identifier or a free-text search — and no actual status values are enumerated.

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?

"What this record is missing and why each one is open" states a specific resource (gaps open on a record) and the payload (reason per gap). It is clearly distinct from siblings like record_overview or list_sources. It never states an explicit verb (list/return) or which record, but the resource is unmistakable.

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?

"Call it before concluding a figure exists" is a concrete, actionable trigger with a stated failure mode it prevents. It does not name sibling alternatives or say when not to call it, but the use condition is explicit rather than inferred.

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