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

Goes well beyond the sparse annotations: discloses that rules REPLACES the whole list, that an empty list removes all rules, optimistic-concurrency refusal semantics, that deletions occur at the next daily run with space reclaimed only at weekly GC, built-in protections (newest image always kept, last-7-day pulls kept), and the credentials.write requirement.

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-loaded with purpose before the mechanics, and nearly every sentence carries needed information given the complexity. It is a dense wall of text, but the length is largely justified rather than padded.

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 mutation tool with no output schema and nested objects, it covers side effects, protections, auth, concurrency, error behaviour, and deferred deletion costs. Nothing an agent needs in order to call it correctly is missing.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning: rules-replace semantics, reset_default vs default mutual exclusion, expected_version being the retention.version from get_registry_storage, and pattern syntax rules (lowercase, * within a segment, ** across segments, bare ** refused).

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 (change) and resource (the images the organisation's registry keeps) plus the goal ('so it stops filling up'). It distinguishes itself from siblings by naming get_registry_storage for reading and run_registry_retention for immediate deletion.

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?

Explicitly covers when to use each option: default vs rules vs reset_default, that omitted fields stay unchanged, that rules must be read via get_registry_storage first, and the concurrency protocol (read again and rebuild, never retry the same arguments). It also routes immediate deletion to run_registry_retention.

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