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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds useful behavioral context beyond that: results are claims paired with an attributed quotation, and scoping is possible via run_id. It stops short of describing ranking, pagination, or empty-result behavior.

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 tightly packed sentences plus a compact example. Core purpose leads, routing guidance follows, and no sentence is redundant.

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?

There is no output schema, so the description carries the burden of describing return values — and it does ('each with the quotation that supports it', attributed quotes). Combined with routing guidance and a usage example, an agent has everything needed to call this correctly.

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 100%, so the baseline is 3. The description adds meaning on top: query should be phrased as a single factual statement/sentence, and the worked example ({"query":"GPAI obligations apply from August 2026","limit":20}) concretely shows the expected query phrasing and limit usage.

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?

Names a specific verb+resource ('Search the atomic CLAIMS runs extracted') and immediately defines what a claim is (a factual statement plus its supporting quotation). It distinguishes itself from the closest sibling, search_notes, by contrasting statement-level vs topic-level search.

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?

Explicitly states when to use it ('check whether one specific factual statement is already evidenced'), when to use the alternative ('Use search_notes instead when the question is a topic rather than a statement'), and the follow-up path ('follow a claim back with read_note for its context'). It also names the narrowing condition for run_id.

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