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

Adds meaningful context beyond annotations: it is free, local, requires no token, and describes what data is returned (id, name, authority, download URL, score scale, disclaimer). Annotations already cover readOnly/idempotent safety, so this fills in the auth/cost/return-content gaps well.

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 tight sentences, front-loaded with the key traits (free, local, no token) and then the return contents and the use case. No padding.

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?

Complete for a zero-param, read-only discovery tool with an output schema. It covers cost, auth, return fields, and the downstream action, leaving nothing an agent needs 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?

Zero parameters, so baseline is 4. The description consistently reflects that no input is needed, reinforcing the zero-param nature without wasted explanation.

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 (list) and resource (sanctions sources), and clarifies it returns metadata about the lists that screen_names checks. It is distinguishable from its sibling screen_names by being the discovery/metadata tool, though the phrasing is somewhat compressed.

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 says when to use it: to pick the lists parameter for screen_names, or to cite sources. It also names the sibling screen_names and frames this tool as the prerequisite for using it correctly.

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

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

Annotations already cover read-only/idempotent/open-world safety, and the description goes well beyond them: it discloses the APIFY_TOKEN requirement, per-name billing, that lists are downloaded fresh at run time, that the underlying Actor is fairquery/sanctions-watchlist-screener, and that results can contain false positives and miss matches. This is exactly the extra operational context annotations cannot express.

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 dense throughout, but the sentence enumerating output fields (status, best_score, matches, aliases, programs, countries, DOB) is largely redundant since an output schema exists. Otherwise every clause earns its place.

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 7-parameter screening tool with an output schema, it covers the essentials an agent needs — auth, cost model, data freshness, accuracy limits, and the matching semantics. The remaining gap is that undocumented parameters (minScore, maxMatchesPerName, excludeNonMatchingCountry) are left to the schema alone.

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 57%, so the schema documents part of the surface (lists, names, queries, minScore default). The description adds the per-name country/DOB filter concept and notes entity type usage, but says nothing about minScore, maxMatchesPerName, or excludeNonMatchingCountry. Baseline 3 fits given partial coverage and partial compensation.

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 — 'Fuzzy-match people or company names against OFAC SDN + Consolidated, EU, UK and UN sanctions lists' — with named data sources and scoring semantics. An agent can separate this from the sibling list_sources (which merely enumerates sources) without opening either 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: it names the inputs (names, optional per-name country and dateOfBirth filters) but never says when to choose this tool over list_sources or when screening is inappropriate. The warning to 'Review every potential match manually and consult official sources and legal counsel' is a caveat, not usage routing.

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