cf-exclusion-check

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

With only readOnlyHint=true declared, the description carries real behavioral weight: it discloses tiered pricing with exact dollar amounts, that charging happens once via x402, that an invalid item is reported in place rather than failing the call, and that an all-invalid batch is refused before any charge. These are cost and failure-mode facts an agent cannot get from annotations or schema.

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?

Three dense sentences with zero filler: capability first, then the decision-relevant pricing tiers, then the failure semantics. The most important routing fact (batch vs. exclusion_check) is front-loaded.

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 read-only batch screening tool with no output schema, the description covers cost, partial-failure behavior, and refusal semantics well. It leaves the item field semantics and any notion of the response payload or latency unaddressed, which is a minor gap given the sibling tools and annotations cover the rest.

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 0% and the single parameter is a nested array of items whose fields (name, dob, state, npi, uei, cage) are entirely undocumented except 'ref'. The description repeats the 2-200 range that the schema already enforces via minItems/maxItems but adds nothing about what makes a valid item or how the fields are used, so it fails to compensate for the coverage gap.

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 ('Screen'), resource ('people/businesses'), and scope ('2-200 ... in one call'), and explicitly ties itself to the sibling 'exclusion_check' whose sources it shares. An agent can immediately distinguish it from exclusion_check (single) and exclusion_sources (source listing) 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?

The phrase 'in one call' plus the reference to exclusion_check implicitly routes the agent: use this when you have many items, use exclusion_check for one. However, it never states that exclusion_check is the alternative for a single item or when the batch tool should not be used, so the guidance is clear context rather than explicit when/when-not.

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?

Rich beyond the readOnlyHint annotation: discloses per-call cost ($0.05 via x402), the return shape (verdict, confidence, basis, reason), and the critical limitation that a match is a name match unless made on an identifier and is not an identity determination. This is exactly the behavioral context an agent needs.

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?

Four tightly packed sentences, front-loaded with the core action and sources, followed by cost, return values, and the crucial match caveat. No wasted words.

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?

Covers the two sources, per-call cost, return shape, and the name-vs-identifier matching distinction. For a read-only screening tool with a fully documented schema, nothing material 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%, so the schema documents all six parameters thoroughly. The description adds meaningful value by clarifying the match-strength hierarchy (npi/uei/cage are strong identifiers vs. name matching), which informs how to weight the inputs, though it doesn't restate the individual formats.

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 (Screen) and resource (person or business) against two named, concrete data sources (LEIE and SAM.gov exclusions). The scope is unmistakable and clearly distinct from the sibling batch and sources tools.

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?

Implicitly positions this as the single-entity check in contrast to exclusion_batch_check, but never names the sibling or the condition (single vs. bulk) that selects it. The pricing note and the match-type disclaimer give useful framing, yet no explicit when-not-to-use guidance is offered.

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 only supply readOnlyHint=true, and the description adds genuine behavioral context beyond that: the operation is free, the freshness signals returned (load dates, completeness, whether a bulk reseed is due), and the exact cost tiers of the downstream paid tools. It stops short of describing output shape in detail, which a 4 reflects.

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?

Three compact sentences, front-loaded with what is listed, followed by cost positioning against siblings. Every clause carries distinct information with no repetition.

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 zero-parameter read-only listing tool with no output schema, the description supplies everything an agent needs: what is returned (counts, dates, completeness, reseed flag), that it is free, and which paid sibling to call for actual screening.

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 tool takes zero parameters, so per the baseline there are no parameter semantics to explain; the description does not need to and does not attempt to. Baseline 4.

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 ('List the loaded exclusion sources (OIG LEIE and SAM.gov)') and enumerates exactly what the listing contains: row counts, load dates, completeness, reseed status. It is clearly distinguishable from the sibling screening tools by naming them and their function.

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 routes the agent: this tool is free metadata, while actual screening is paid via exclusion_check (single name) or exclusion_batch_check (2-200 names, tiered pricing). When-to-use and the alternatives are both stated outright.

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