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

Beyond the readOnlyHint annotation it discloses ordering (newest first), the access-scoping rule (only decisions in your project/clusters), the full status lifecycle, and per-item fields including can_decide/can_run evaluated for the caller — exactly the authorization context an agent needs before deciding whether to act on a proposal.

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 the identity and scope in the first clause, with filtering and read-only caveats at the end. It is a dense single paragraph; the CLI-parallel parenthetical and the long status enumeration consume space without adding agent-relevant meaning.

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?

There is no output schema, and the description compensates by enumerating the returned fields (status, plan, plan_hash, expected saving, runnability, can_decide/can_run). Combined with the scoping and ordering notes, an agent has everything needed to call it and interpret results.

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 both parameters are already documented; the description only adds the framing that status narrows and limit caps the result. The enumerated status values duplicate the schema rather than extend it, so baseline 3 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?

States a specific verb+resource (listing the organisation's cost decisions) and immediately defines what those objects are (right-size, off-hours, released-volume proposals filed by cost surfaces). It also implicitly distinguishes itself from the mutation siblings (approve/hold/set_aside/execute/release_cost_decision) by describing the objects those siblings act on.

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?

Gives clear context for use: review proposals within your reach, newest first, optionally narrowed by status or capped by limit, and flags it as read-only so an agent knows to route mutations elsewhere. It never names an alternative tool explicitly (e.g. get_cost_decision for a single item), so it stops short of full when-to-use/when-not guidance.

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