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

Goes well beyond the annotations (destructiveHint=false, openWorldHint=false) by disclosing side effects and their limits: uninstall removes only the install while built artifacts keep working, rollback restores as a new version rather than overwriting, reports are one per account and enough of them hide the template. It also names the failure modes the caller will hit (cannot_rate_own, not_installed, rate_limited, permission_required) and the nextStep return for install.

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?

Dense but well-ordered: an upfront scope statement that this tool never deletes, then one semicolon-delimited clause per action. Nearly every clause carries operative information (limits, error codes, return fields), with only slight density cost from packing six actions into one paragraph.

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?

Covers what matters for a 7-parameter multi-action tool with no output schema: per-action effects, rate limits, error codes, and the one documented return value (install's nextStep). An agent could invoke any of the six actions correctly from this text alone, though it never indicates what the other actions return.

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 only 43% schema description coverage, the description compensates by tying parameters to actions: stars is the person's 1-5 rating, kind and reason (<=1000 chars) are report-only, and version is the one restored as a new version on rollback. slug and action are largely self-evident from the enum, leaving only minor residual ambiguity about version's meaning for non-rollback actions.

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 opener 'Act on one template' is generic, but the body enumerates each of the six actions with a concrete effect (install/uninstall the workspace's installed set, rate with 1-5 stars, report for a moderator, rollback a version, request verification). It explicitly contrasts itself with the reading sibling ('Finding and reading templates is super_templates'), so an agent can pick it apart from alternatives without opening the schema.

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?

Gives per-action preconditions that function as when-to-use rules: rate only on an installed template that isn't yours, rollback only if the runtime didn't change, verification capped at 3 per 30 days, and a clear exclusion ('nothing here deletes a template, a version or a built artifact') plus routing to super_templates for lookup. It does not distinguish this tool from the other template-write siblings (super_template_save, super_release_template), which keeps it from a 5.

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