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 the org-admin requirement for set, the 100-template quota, that archive sets status=retired and that restore appends an active copy, that a new run of an overridden seed reverts to the seed, and that running instances keep their snapshot. It leaves permission requirements for archive/restore and any failure modes other than the version conflict (documented in the schema) unstated.

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 the resource identity, then an action-by-action tour in terse, information-dense clauses. Nearly every sentence carries distinct semantics (versioning, override, retirement, quota, snapshot), though the run-on style with quoted literals could be harder to scan than a structured list.

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?

An output schema exists, so return values need no explanation, and the description still covers the lifecycle an agent needs: seed vs org versions, versioning/conflict flow, retirement/reversal, quota, and run snapshot isolation. Nothing required to call a 7-parameter registry tool correctly appears 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds workflow meaning rather than restating field docs: it ties version ('reads one with its version') to expected_version ('pass it as expected_version on set') into a read-then-compare-and-set cycle. It does not add syntax detail for slug, definition, or include_retired beyond the schema.

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 definition names the exact resource (the org's process template registry) and enumerates the five actions it multiplexes: list, get, set, archive, restore. It implicitly separates itself from the sibling process_run_* family by framing everything as the template registry rather than runs, and the seed-vs-org-version scope is explicit.

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?

Each action's context is stated: 'list' to see start points, 'get' to read one version, 'set' to append a new version, 'archive' to retire the head, 'restore' to re-activate a retired head. It also flags that set is org-admin and that expected_version is required for archive/restore. It does not, however, explicitly contrast with neighboring tools such as process_run_create when an agent might be unsure whether to edit a template or start a run.

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