bdesign_workflow_template_apply

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

Annotations already declare idempotentHint=true and destructiveHint=true, and the description adds real value by explaining the optimistic-concurrency contract ('explicit IDs and revisions are required; no automatic generation'). It stops short of saying what happens on a revision mismatch (conflict error vs. overwrite) and gives no warning that 'remove' is irreversible, which is the key behavioral fact for a destructive tool.

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?

Three tight sentences, front-loaded with the command set before the revision rules. No filler or restatement of the name; the only mild inefficiency is that the revision rule and the ID rule are split into separate sentences when they describe the same contract.

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 five-parameter, four-variant selector tool with no output schema and 0% field documentation, the description is thin: it omits idempotency semantics, project scoping, conflict/failure behavior, and any hints about the nested command payloads. An agent would still need to reverse-engineer much of the schema to call this correctly.

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 0%, so the description carries the burden, and it only explains one of the five top-level parameters (expectedRevision) in any depth. commandId, idempotencyKey, and projectId get no mention, and none of the per-variant fields (selectedCardIds, definitionDigest, templateRevision, bindings, placement, instanceId) are explained, even though they are the most error-prone part of the payload.

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 specific verbs (capture, rename, remove, instantiate) against a specific resource (workflow template), so an agent knows this is the mutation entry point rather than the read siblings (template_list, template_get, template_preview). It does not name those siblings explicitly, so differentiation is inferred from the verb set rather than stated.

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 description gives genuinely useful conditional guidance on which revision value to pass per command ('zero for capture, template revision for rename/remove, Canvas revision for instantiate'). However, it never states when to reach for this tool versus bdesign_workflow_template_preview (a dry-run alternative that matters a lot for a destructive tool) or template_get prior to renaming.

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