list_resources

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

Annotations already mark the tool as read-only and non-destructive, so the description does not need to restate that. It adds meaningful behavioral context beyond annotations: snapshot_id ties results to a specific observation, resource IDs are not globally durable, and hierarchy should be trusted over process-name inference. This is useful boundary-setting that the structured annotations do not convey.

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 description is three compact sentences with no filler. It front-loads the core purpose, then adds essential snapshot and hierarchy caveats. Every sentence contributes unique information that is not already present in the input schema or annotations.

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?

For a read-only listing tool with nine optional parameters and no output schema, the description covers the key behaviors: what is found, how to scope results to a snapshot, and how to interpret the returned hierarchy. It does not detail output format or pagination, but those are less critical given the tool's simplicity and the schema's parameter descriptions for the more nuanced fields.

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 only 44%, and the description partially compensates by referencing CPU/memory as sorting dimensions, generic filters, a limit, and snapshot_id reuse. It does not clarify important parameters like environment, resource_kind, parent, or sort_order beyond their schema names and enums. The description adds some semantic context but leaves a meaningful gap for the undocumented or under-documented parameters.

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 clearly states the tool finds processes, applications, containers, or infrastructure using CPU/memory, filters, and a limit. It names the key resource types and the filtering dimensions, so the agent can infer the general capability. However, it does not explicitly contrast with sibling tools like list_children or inspect_resource.

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?

The description gives valuable operational guidance: reuse snapshot_id for follow-ups, treat resource IDs as scoped to that observation, and rely on the returned hierarchy rather than inferring container membership from names. It does not, however, state when to choose list_resources over list_children or get_system_summary, so the when-to-use guidance is implied rather than explicit.

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