compute_governance_taintCalculates an artifact's governance taint level from its derivation chain and revoked sources, so you can assess trust risk and policy impact.
Compute governance taint level for an artifact based on its derivation chain and revoked sources.
| Name | Required | Description | Default |
|---|---|---|---|
| artifactId | Yes | ||
| revokedSources | No | Source IDs that have been revoked |
Changes observed during successful MCP inspections.
v4.0.0Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falsev2.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds that the result is a function of the derivation chain plus revoked sources, but says nothing about whether the value is persisted or computed on demand, or any auth/scope requirements. Adequate but not rich.
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?
One sentence, front-loaded with the verb and outcome, no filler. It is efficient, though it is short enough that the missing usage and return-value context is felt.
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, so the description should convey what a 'taint level' looks like (numeric scale, categorical tier, threshold semantics). It does not, leaving the agent unable to interpret the result. Input semantics are otherwise adequately implied by the one sentence.
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 50% – revokedSources is documented in the schema itself, while artifactId is not. The description implies both inputs but adds no format, ID convention, or semantics for artifactId beyond what the name conveys. Baseline 3 is appropriate given partial schema coverage.
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 ('compute') and a specific resource ('governance taint level') and names the two inputs it derives from (derivation chain, revoked sources). It does not differentiate itself from near neighbours such as evaluate_revocation_impact or resolve_rights_propagation, so it falls short of a 5.
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?
There is no when-to-use guidance, no prerequisites, and no named alternative among a very large sibling set. The agent must infer from the phrase 'derivation chain and revoked sources' when this tool is the right call versus evaluate_revocation_impact or check_aggregate_constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.