compute.check_storage

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

Annotations already declare readOnlyHint=true, and the description usefully reinforces this by asserting no files are deleted, which is meaningful reassurance in a cluster full of storage-cleanup tools. However, it says nothing about what checks are performed, whether a project must be synced first, or what the "safety issues" consist of, so it adds only modest context beyond the annotation.

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?

A single front-loaded sentence with no filler and no redundancy. Its brevity is a virtue structurally, though it borders on under-specification for the amount of behavior it needs to convey.

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?

With no output schema, zero parameter documentation, and 30 sibling tools including eight other storage operations, the description is too thin. It does not say what evidence is returned or how this differs from scanning or reporting, which is exactly the context an agent needs here.

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 carries the full burden for two parameters and it explains neither. "project storage" weakly implies project_id's role, but the optional node_id is entirely unaddressed, leaving the agent to guess whether it narrows the check to a single node.

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 verb and resource ("Check project storage") plus two vague objects ("evidence and safety issues"), but "storage evidence" is undefined jargon. It does not distinguish this from near-identical siblings such as compute_scan_storage, compute_report_storage, or compute_inspect_node, so an agent cannot tell which to pick from the description alone.

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 statement of when to use this versus the other storage tools in the family, and no exclusions or prerequisites. The only implicit cue is "without deleting files," which hints it is the non-mutating counterpart to the plan/apply storage tools, but that routing is left to inference.

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