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

Annotations cover read-only/idempotent/open-world, so the bar is lower, yet the description goes well beyond them: it defines the output states (GO/HOLD/STOP), the matching policy ('only a full-name match is a hit'), alias coverage, and critical invocation constraints (pricing, x-credit-token auth, no API key, no free tier). This is the auth/cost context annotations cannot carry.

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 core purpose and scope distinction, then layers matching behavior and access/pricing. 'Required input: name' is slightly redundant given the schema, and the pricing/auth cluster is dense, but each sentence carries actionable information for invocation.

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-format detail is not required, and the description still summarizes the decision states. It covers scope, matching policy, cost, and auth method — everything an agent needs to call it correctly. No meaningful gap remains.

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?

One parameter at 100% schema coverage, and the schema already says 'Person or company name'. The description's 'Pass a person or company' and 'Required input: name' largely restate the schema, adding little semantic meaning. Baseline 3 is appropriate when the schema does the work.

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?

A specific verb+resource ('Screen a person or company against the OFAC SDN list') with an explicit scope carve-out: 'Sanctions screening for NAMES, not wallets.' This immediately separates it from the wallet-oriented siblings (sanctions, sanctioned_exposure) without opening a 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?

Clear context for use: pass a person or company name to get GO/HOLD/STOP, and it states it is a screening aid, not a compliance determination. It distinguishes itself from wallet-based screening ('not wallets') but does not name the batch alternative (sanctions_batch) for multi-name workflows, leaving that to inference.

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