system_gc

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

With no annotations, the description carries the full burden and does well: it discloses admin scoping, auditing, the exact namespace targeted, and the safety mechanism (re-listing verification so in-use tags are reported skipped, never removed). It does not cover reversibility of the base operation or what the result looks like, which keeps it from a 5.

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?

Two tight sentences: identity and scope first, safety behavior second. Zero filler and nothing that repeats the schema.

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 3-param tool with a fully documented schema, no output schema, and no annotations, this covers purpose, scope, and the key safety invariant. It would be complete with a brief note on whether the run reports which repos were reclaimed or skipped.

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 100%, so dry_run, idempotency_key, and include_orphan_data are all fully documented in the schema; baseline is 3. The description adds mechanism context (verification re-listing, skip-not-remove) but does not itself explain any parameter's effect.

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 (garbage-collect) and resource (orphan app images) plus the exact namespace it operates on (nerdit-app/*). It clearly distinguishes itself from the rest of the cluster/service-management siblings, though it does not explicitly contrast with the nearest adjacent tool (system_disk).

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 condition for use is implied — orphan image repos with no live workload row — and admin scoping is noted, but there is no explicit 'use this when X, not Y' guidance and no prerequisite/permission statement beyond the parenthetical. Adequate but leaves the agent to infer when to reach for it.

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