yieldsentinel

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

Even with annotations declaring readOnlyHint, openWorldHint, idempotentHint, and non-destructive, the description adds substantial behavioral context: live yieldhunter data fetching, 'Research only — never holds keys', 'verdict is not an exit signal or execution order', and incomplete data always resolving to review/unknown never silent ok. No contradiction with annotations.

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 dense but reasonably organized: purpose, prerequisites, identifiers, required policy inputs, presets, behavior, caveats, and an example. It is front-loaded with the core purpose. Minor redundancy exists ('Scoring ≠ policy approval' appears twice; the 'never silent ok' point is made twice), but overall every major section earns its place for an 18-parameter tool.

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 only one sibling, the description is quite complete: it names the return payload (PolicyVerdict plus A2H summary/suggestedNextSteps/legend), explains missing data behavior, and provides a concrete example. It does not enumerate possible verdict values or provide an output example, but the essential call/invocation context is covered.

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 baseline is 3. The description adds cross-parameter meaning beyond individual schema entries: it explains that policyPreset and/or thresholds are 'Required for a real check', clarifies rwa-selective is not a free pass, defines requireCurated as using the Yieldsentinel allowlist, and maps aliases for poolId/opportunityId/id. This exceeds baseline while not exhaustively describing all 18 parameters.

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 opens with a specific verb and resource: 'Evaluate a described stablecoin yield position against a research policy'. It clearly identifies the tool's scope (research/policy check) and distinguishes it from the 'health' sibling by emphasizing policy, verdicts, and research-only behavior rather than system health.

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 description gives detailed usage conditions: pass a policy preset or explicit thresholds, pass an opportunity id/protocolSlug, and notes that without a policy the verdict is always review/unknown. It says the tool is research-only and not an execution order, which prevents misuse. However, it does not explicitly contrast with the sibling 'health' tool or state when to prefer this tool over alternatives.

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 provide readOnlyHint, destructiveHint, and idempotentHint, lowering the burden. The description adds safety-relevant context not present in the annotations, including that the tool returns system fields and that the service is research-only, non-ccustodial, never holds keys, or executes transactions. This goes beyond a bare readOnly flag. While this statement applies broadly to the service, it remains useful behavioral context for the agent.

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, followed by return value, usage sequencing, and risk context. Every sentence earns its place. The `Example input: {}` line is a low-cost confirmation. The structure is effective size and no filler.

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 the simplicity of the tool and the rich annotations, the description is fully sufficient. It tells the agent what it returns, when to call it, and explicitly routes to the sibling check_position tool. Even without an output schema, the description lists the relevant fields and is clear that no arguments are needed.

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?

With zero parameters in the input schema, there is nothing to explain. The description reinforces this by showing 'Example input: {}', confirming the no-argument contract. Since schema description coverage is 100% and there are no params, the baseline of 4 is appropriate.

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 opens with a specific verb and resource: it is a liveness and capability check for yieldsentinel. It then enumerates the exact returned fields (service status, schemaVersion, policyVersion, feature flags, available tools). It additionally differentiates from the sibling check_position by instructing that this tool should be used first for connectivity verification.

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?

Contains explicit operational guidance: 'Use this first to verify connectivity, then call check_position...' This tells the agent exactly when in the sequence to invoke it relative to the sibling. It also suggests a reasonable default (policyPreset) while allowing explicit thresholdes, preventing arbitrary selection. No misleading or missing guidance.

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