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

The description adds meaningful behavior beyond the annotations: the server recomputes projectionChecksum and rejects host-supplied HTML, CSS, assets, and arbitrary defaults. This helps the agent understand what will be validated and what inputs are ignored, complementing the idempotentHint and readOnlyHint=false annotations.

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?

The description is only two sentences and front-loads the main purpose. It is dense and uses some jargon like 'semantic projection', but every clause carries information and there is no filler.

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 the output schema, annotations, and 100% parameter documentation, the description covers the key context: safe projection, server-side checksum recomputation, and the rejection of custom host inputs. It does not explain the exact template creation behavior, but the overall context is sufficient for an agent to invoke the tool 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 coverage is 100%, so each parameter is already documented with descriptions. The description adds value by clarifying that projectionChecksum is recomputed server-side and that host-supplied content is not accepted, but it does not systematically explain individual parameter usage 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 description clearly identifies the action (save) and the resource (an immutable invoice revision as a reusable workspace template), making the tool's purpose evident. It distinguishes itself from preview_invoice_template_extraction by emphasizing 'confirmed safe' and 'reusable workspace template', though it does not explicitly name a sibling.

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 implies the workflow: only a confirmed safe projection should be saved, and the server recomputes the checksum. However, it does not explicitly state when to use this tool versus preview_invoice_template_extraction or other template-related tools, leaving prerequisites and exclusions mostly implicit.

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