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

Annotations only cover the read-only/idempotent safety profile; the description adds substantial context beyond them: GET-only calls to the Apify API, the exact key-value store name, 'never writes', typical latency (<1 s, up to ~3 s in a fallback path), the ~1.6 MB gzip read fallback, free-of-charge status, the APIFY_TOKEN requirement, and the specific error codes including which are retryable.

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?

Strongly front-loaded with WHAT/WHEN/WHEN NOT/BEHAVIOR/COST/RETURNS/PARAMETERS/EXAMPLE headings, so an agent can scan to the relevant section. It is verbose in places, and the long inline EXAMPLE return dump partly overlaps with the output schema, but nearly every sentence carries actionable information.

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 single-parameter, free read tool with a full output schema, this covers everything needed: trigger conditions, cost, token requirement, failure modes, and the meaning of the freshness window. Nothing required to call it correctly 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 coverage is 100% and already documents the 0-12 range and default of 6, so the baseline is met. The description adds genuine semantics beyond the schema: what 'fresh' means (downloaded within maxAgeHours AND non-empty), that stale lists are re-downloaded rather than screened, that maxAgeHours=0 marks everything stale, and what store_found and read_from indicate.

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 (Show), a specific resource (sanctions list cache freshness), and enumerates the exact lists covered (OFAC_SDN, OFAC_CONS, EU, UK, UN). It explicitly distinguishes itself from both siblings, naming screen_names and list_sources as the tools this is not.

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?

Has explicit WHEN TO USE (before large/time-critical screen_names batches, or to document list currency in a report) and WHEN NOT TO USE (screening names, listing sources), naming the alternative tool for each case. It also clarifies that this tool does not refresh the cache.

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 safety (readOnly, idempotent, non-destructive, non-open-world), and the description adds context beyond them: free, local, no network, no APIFY_TOKEN, does not download lists, and that the sibling screen_names is paid per name. These cost and execution-locality details materially affect when and how an agent calls it.

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?

Labeled sections (WHAT, WHEN TO USE, WHEN NOT TO USE, COST, RETURNS, PARAMETERS, EXAMPLE) front-load the purpose and the routing decision. The longer length is earned by information density, and the concrete example call clarifies the practical handoff to screen_names.

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?

Given an output schema exists, return values need no full explanation, yet the description still summarizes sources[].id and score_scale for practical use. Cost, locality, usage boundaries, and the screen_names handoff cover everything an agent needs to call this zero-param tool correctly.

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-parameter tool, so the baseline is 4; the schema is empty and fully self-documenting. The description explicitly states 'PARAMETERS: None; the result is static and cannot be filtered,' which usefully prevents wasted attempts to filter, though there is little parameter meaning left to add.

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: a static list of the official sanctions lists that screen_names checks, including id, name, issuing authority, download URL, score scale, and disclaimer. It also names the siblings screen_names and list_cache_status, so an agent can distinguish it without opening any 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?

Explicit WHEN TO USE (choosing the lists parameter, citing sources, explaining coverage) and WHEN NOT TO USE (screening a name -> screen_names; cache freshness -> list_cache_status; does not download lists). It routes the agent to the correct alternative for each adjacent need with no inference required.

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?

Goes far beyond the readOnly/openWorld/idempotent annotations: it discloses cache lifetime (6 h), load latency (~2-5 s cached, ~10-40 s re-downloaded), throughput, the exact pay-per-event price model ($0.003/name + $0.007 start fee, error rows free), billing for non-matches, and that failed list downloads degrade to lists_unavailable rather than failing the run.

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?

Long but deliberately so for a complex, paid, cost-incurring tool. Sections are labelled (WHAT / WHEN TO USE / WHEN NOT TO USE / COST / RETURNS / EXAMPLE / PARAMETERS / LIMITS), front-loaded with purpose and cost, and each section carries non-redundant operational facts.

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, yet the description still summarises the row shapes (type=screening with status/matches[] vs. free type=error rows) and adds an end-to-end example. Cost, latency, limits/liability caveats, and edge cases (INPUT_EMPTY, lists_unavailable) are all covered, so nothing an agent needs to call this correctly 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 coverage is 100% (baseline 3), but the description adds meaning the schema cannot: it flags that names and queries are both schema-optional yet at least one is required, explains billing per entry, entityType precedence (query value wins), dateOfBirth ±1-year drop behavior, country semantics with excludeNonMatchingCountry, and minScore tuning guidance (90-95 large batches, 75-80 transliterated).

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?

Opens with a specific verb+resource: 'Fuzzy-match people or organisation names against the OFAC SDN, OFAC Consolidated (non-SDN), EU, UK and UN sanctions lists.' It names the exact sources and matching semantics (order-, case-, diacritics-insensitive), and the WHEN NOT TO USE section explicitly differentiates it from the siblings list_sources and list_cache_status.

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?

Explicit WHEN TO USE (KYC/KYB onboarding, vendor/counterparty checks, bulk re-screening) and WHEN NOT TO USE with named alternatives (list_sources for coverage/citation, list_cache_status for freshness). It also states the batching condition — put all names into one call — leaving nothing to inference.

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