risky_changes

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses that output is ranked, that it is findings-only ("resources not mentioned had nothing notable"), and critically that attribute values are never printed, which tells the agent to fetch details elsewhere rather than expect values here. It omits pagination/limit behavior and does not state whether this is a static analysis of a plan file, so it falls short of full transparency.

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 definition is front-loaded with the core claim and then spends its length on a dense but purposeful flag taxonomy where each item adds a distinct risk category. It is somewhat run-on in the parenthetical enumerations, but no sentence is 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?

An output schema exists, so return values need not be explained, and the description covers the behavioral and severity side well. The remaining gap is the input contract: for a required `path` argument with zero schema documentation, the description should state what kind of artifact to point at, and the limit/truncation semantics of the ranked list are unaddressed.

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%, so the description must compensate. It fully specifies min_severity with its five enum values (info|low|medium|high|critical), which the schema does not, but it says nothing about the required `path` parameter (plan file? directory? plan JSON?) or about what `limit` bounds, leaving two of three parameters, including the required one, to guesswork.

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 opening sentence gives a concrete verb+resource ("Ranked list of risky changes with reasons") and the following enumeration makes precise what counts as a risky change, so an agent knows exactly what this returns. It never names siblings like list_changes or plan_summary, so the boundary between this risk-scoped view and a plain change list is left implicit.

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?

Usage is implied by the content: the flag taxonomy makes clear this is the tool for security/destructive-change triage, and the min_severity levels signal how to widen or narrow scope. However, there is no explicit when-to-use statement, no when-not-to-use, and no routing to alternatives such as list_changes for a full inventory or diff_resource for a single resource.

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