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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely non-obvious context: pricing (0.005 USDC via x402 or 3 credits), a 5-free-calls-a-day allowance, and the legal distinction that these are trade restrictions, not asset freezes. What it omits is what a hit looks like — match score, list provenance, or confidence bands — which matters for an open-world screening tool.

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-loads the trigger and the scope, then packs coverage, exclusions, inputs and pricing into two dense sentences with no filler. The parentheticals do real work (which agencies' lists, what the ban means) rather than restating the title.

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 no output schema and a screening tool whose value depends on interpreting hits, the description should say roughly what comes back (match/no-match, score, list source). It also advertises a threshold that does not exist, so an agent cannot tell how to tune sensitivity. Everything else — pricing, eligibility for free tier, key handling pointer — is present.

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?

The description's input line claims 'name, optional type (entity or person), threshold', but no threshold parameter exists in the schema — a misleading statement about the call signature. Meanwhile the api_key parameter, which the schema documents well, is never mentioned in the description. With 67% schema coverage the schema carries most weight, but the phantom threshold parameter actively degrades correctness.

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 — screens a name against the US Consolidated Screening List and the DHS UFLPA Entity List — and explicitly carves out the SDN list as belonging to a different (sanctions) screen. The agent can distinguish this from eu_sanctions_screen or pep_screen by coverage rather than guesswork.

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?

Gives a concrete trigger: 'Use before buying from, selling to or shipping to a company, above all a Chinese or Russian one,' and draws the boundary against the sanctions screen via the SDN exclusion. It stops short of naming the sibling sanction tools (eu_sanctions_screen, pep_screen) or saying when this is unnecessary (e.g. pure EU-only exposure).

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