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

Well beyond the readOnly/idempotent/closed-world annotations, it discloses commercial and operational traits an agent would otherwise not know: one charge per report, names are never logged, matching is deterministic (no AI) and runs offline against a bundled snapshot, and stale snapshots surface as warnings. The full response envelope (result, data_confidence, estimated_items, sources, data_version, warnings, disclaimer) is spelled out.

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?

Front-loaded with purpose and output artifact, then progressively adds commercial terms, response shape, and list coverage — a sensible ordering. It is dense and the run-on middle clause enumerating report contents could be tightened, but almost every sentence carries information an agent needs.

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 billing-relevant screening tool with an output schema, the description covers what is produced, what a clear result looks like, privacy handling, offline determinism, cost, and failure signalling via warnings. Nothing material for correct invocation or interpretation is missing.

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 parameter meaning is already carried structurally, and the description largely restates the list enum and threshold semantics already present in the schema. The worked example (subjects array with name/dob, case_reference, prepared_by) adds modest value by showing shape in practice, but no new parameter semantics.

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 first clause gives a concrete verb and resource — screens 1–50 subjects and returns a self-contained HTML report named result.html — which tells an agent exactly what artifact it gets. It doesn't name the sibling tools (screen_batch, screen_name, explain_match), so the differentiation from screen_batch in particular is left implicit rather than stated.

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?

There is implied usage context ("suitable for the client's AML file") and threshold guidance is carried by the schema, but the description never says when to choose this over screen_batch or screen_name. An agent must infer the routing decision from the report-output phrasing rather than being told.

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