yieldsentinel

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is clear. The description adds behavioral context: incomplete data yields 'review/unknown', presets affect exclusion behavior, requireCurated uses an allowlist, and it explicitly states this is research only, never holds keys, and is not an exit signal. This goes beyond annotations, though it could mention rate limits or latency.

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?

The description is front-loaded with the core purpose and key usage rule, but it is somewhat repetitive: policyPreset options are listed twice, and the requireCurated behavior is restated. The example is useful but adds length. Every sentence mostly earns its place, but there is redundancy.

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 18 parameters, no output schema, and rich annotations, the description covers the essential behavioral traits: what happens with no policy, how presets work, what requireCurated means, and that scoring is not approval. It also clarifies the return (PolicyVerdict + A2H). It could be more complete by describing pagination or the exact fields of PolicyVerdict, but for a research tool with no output schema, it is sufficient.

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 100%, meaning every parameter is documented in the schema. The description repeats some parameter examples (poolId, policyPreset, minScore, etc.) but adds no new semantic meaning beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The description states a specific verb and resource: 'Evaluate a described stablecoin yield position against a research policy (pull).' This is clear and distinguishes the tool from the sibling 'health' tool, which serves a different purpose. However, it does not explicitly differentiate itself from alternatives beyond the single sibling, and the parenthetical '(pull)' is cryptic.

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?

Provides explicit when-to-use condition: 'Always pass your policy rules (or a preset). Without a policy, no meaningful check is possible — the verdict will be review/unknown, never ok.' It also specifies what is required for a real check. However, it does not explicitly state when NOT to use this tool or name alternatives (there is only one sibling, 'health', which is unrelated).

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the side-effect disclosure: the health ping 'may refresh research vintage' via an external dependency, plus the caveat that dependency health ('YH healthy') does not imply service health ('≠ YS ok'). It also clarifies the non-custodial nature and that no transactions are executed. It stops short of documenting latency, caching, or rate limits, but the behavioral picture is substantial.

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 what the tool is and what it returns, then usage ordering, then caveats — a sensible progression. It is slightly cluttered: the check_position policyPreset list and the 'non-custodial; never holds keys' disclaimer are somewhat tangential for a zero-parameter health probe, and the shorthand 'YH ≠ YS' assumes prior context. Still, nearly every sentence carries operational signal.

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?

No output schema exists, and the description compensates by enumerating the returned fields (status, schemaVersion, policyVersion, feature flags, available tools). For a zero-parameter, read-only liveness probe with full annotation coverage, nothing an agent needs in order 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?

Zero parameters and 100% schema coverage, so the baseline is 4. The description adds the explicit 'Example input: {}' confirming a no-argument call, but nothing further is needed or offered. The policyPreset enumeration mentioned belongs to check_position, not to this tool's schema, so it doesn't add parameter meaning here.

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 — 'liveness and capability check for yieldsentinel' — and enumerates what it returns (status, schemaVersion, policyVersion, feature flags, tool list). It also explicitly distinguishes itself from the only sibling: 'a verdict still requires check_position' and 'YH healthy ≠ YS ok.' An agent can tell this apart from check_position 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?

Explicit sequencing: 'Use this first to verify connectivity, then call check_position with policyPreset treasury-conservative | balanced-research | rwa-selective.' It names the alternative tool, the order of operations, and the handoff condition. Nothing about when to prefer this over the sibling is left to inference.

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