Render Codecollection Skill

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 explicitly disclaims git push and workspace mutation, discloses the side-effect of writing .runwhen files to disk, and states the environment precondition. It stops short of covering failure modes, whether rendering is idempotent, or how output_dir behaves on invalid input, so it is strong but not exhaustive.

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 one-line purpose, then segmented into skills, emitted layout, non-goals, platform defaults, and preconditions using bold and short paragraphs. Slightly long for a tool definition and repeats the git non-goal mildly, but every block carries distinct routing or behavioral information.

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?

Given 35 parameters and an existing output schema (so return values need no explanation), the description covers the pieces an agent cannot infer: the emitted file layout, the platform-dependent generation rule, required runtime environment, and the git hand-off boundary. Remaining gaps — error handling, idempotency, and any limits on repeated rendering — are minor rather than blocking.

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 coverage is 100%, so the baseline is 3; the description adds genuine meaning by grouping the discovery-related parameters — platform default 'runwhen' vs kubernetes/azure/aws/gcp per-resource discovery, and the paired resource_types/match_rules/slx_qualifiers sourced from the bundled indexer catalogs. It explains base_name (<15 chars, defaults to bundle_name) and the base64 GEN_CMD delegation, going beyond the schema text.

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 and resource ('Render a tested tool-builder task as a private Custom Discovery CodeCollection') and immediately enumerates the concrete artifacts emitted (generation rule + Jinja templates, .runwhen/SKILL_TEMPLATE.md, raw_script files). This clearly separates it from siblings like commit_slx or deploy_registry_codebundle, which the agent can rule out without opening a 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?

Names the prerequisite workflow explicitly via the runwhen-skill URIs ('build-runwhen-task (authoring + testing first)') and draws the boundary against git operations: 'does not push to git or mutate the workspace — it renders files locally ... for you to git add / commit / push.' It also routes platform selection to list_discovery_platforms/list_indexed_resource_types and states the 'Requires runwhen-local with the matching platform indexer enabled' precondition.

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