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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description still earns credit by disclosing domain semantics an agent could not guess: inheritance is resolved by taking the strictest value along the path, and locked keys block overrides below them. That is exactly the kind of behavior that changes how an agent interprets results. It does not mention caching, whether results are computed live, or ordering of the returned entries.

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 tight sentence with a parenthetical that carries the two highest-value facts (strictest-wins, locks block below). No filler or repetition of the title. The main claim could be front-loaded with an explicit verb to improve scannability.

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?

The tool is simple (one optional param, read-only, output schema present so return shape needn't be spelled out), and the inheritance semantics are well covered. However the node parameter's meaning and default scope are left unexplained, which is the one thing an agent actually needs to call this correctly in a hierarchy.

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 single parameter 'node' has 0% schema description coverage and a bare default of 'current', so the description must carry the burden — but it never explains what the node argument does (scope the evaluation to a subtree? a specific node id? a path?). The phrase 'the node it comes from' describes returned provenance, not the input. This is a real gap at 0% 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?

The description identifies the resource (policies in force at a scope) and, crucially, explains what 'effective' means: inherited resolution where 'the strictest value along the path wins' and 'locked keys cannot change below.' That distinguishes it from the mutating sibling set_policy and from audit/lineage readers without opening a schema. It is phrased as a noun phrase rather than an explicit verb ('returns...'), which keeps it just 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 or when-not-to-use guidance and no named alternative. An agent must infer that this is the read counterpart to set_policy and that get_audit_view or get_lineage serve different questions. No prerequisites, no mention of what scope the result covers by default.

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