bdesign_workflow_template_preview

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

Annotations already declare readOnlyHint=true, and the description adds real value on top by naming the side effects explicitly avoided (no writing, uploading or generating) and by disclosing what comes back: a source revision/digest or draft blockers. It does not explain what a 'draft blocker' is or how failures surface, which keeps it below a 5.

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?

Two tight sentences with no filler, and the read-only guarantee is front-and-center at the end of the second clause where it matters most. Slightly compressed to the point of terseness, but nothing is wasted.

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 preview-only tool with readOnlyHint and no output schema, the description covers the essentials: two modes, no side effects, and the general shape of the return (revision/digest or blockers). It stops short of explaining the blocker concept or the meaning of the nested binding/placement parameters, which is a meaningful gap given the depth of the input schema.

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% and the schema is a nested anyOf with bindings, placement, instanceId, templateRevision and projectId, none of which the description explains. It does add the one piece of meaning the schema cannot convey: that selectedCardIds corresponds to capturing Canvas steps and templateId/templateRevision corresponds to exact-revision insertion. That disambiguates the union but leaves bindings and placement semantics entirely undocumented.

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 the verb (preview) and the two distinct resources it can preview: a capture of selected Canvas steps, or an exact template revision insertion into a project. The two-mode framing maps cleanly onto the schema's anyOf branches, so an agent can tell which mode it is aiming at, though the phrasing 'Preview capturing... or inserting' is grammatically awkward.

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 word 'Preview' plus 'without writing, uploading or generating' implies this is the dry-run step before an apply, but no sibling is named and no explicit 'use this before bdesign_workflow_template_apply' routing is given. Usage is inferable from context rather than stated, leaving the agent to guess whether a preview is mandatory before applying.

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