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

Annotations cover the safety profile (readOnly false, destructive false, openWorld false), and the description adds genuinely new behavior: per-name credit cost, the audit-oriented nature, and the crucial caveat that hits are only candidates requiring further assessment rather than confirmed matches. It does not restate annotation content, though it stays silent on latency or failure modes.

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?

Four short sentences, front-loaded with purpose and scope, and no filler. The sentence enumerating response fields (record id, snapshot version, data-as-of dates, engine version) partially duplicates the output schema, which is the only mildly redundant element.

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 an output schema present, return values need not be described, and the description still covers scope, cost, idempotent-retry implications, and the review caveat. Remaining gaps (what threshold defaults to, processing time for 100 names) are minor for this tool class.

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%, so the schema already documents names, dob, type, country, threshold, and idempotency_key. The description adds only the batching cap ('1 to 100') and the one-credit-per-name cost model; it says nothing about the threshold parameter, so the baseline 3 is appropriate.

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 and resource ('sanctions screening of 1 to 100 names') plus scope ('against 10 official lists'), which cleanly separates it from siblings get_balance, get_record, and list_sources. An agent can identify this as the screening action without opening the schema.

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 rather than stated: screening is what this tool does, and 'hits are candidates for human review' hints at the downstream workflow. It never names an alternative or a when-not condition (e.g. use get_record to re-fetch an existing screening), so routing must be inferred.

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