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

Annotations already declare the safe read-only profile (readOnlyHint=true, destructive=false, openWorld=false), so the bar is lower, yet the description still adds substantive behavior: the content-vs-blocks return shape, the separate letterhead/brand selection step, and the MERGE_FIELDS_MISSING error that lists missing/invalid fields. It stops short of disclosing permissions or pagination/size limits, so 4 rather than 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?

Purpose is front-loaded and every clause is actionable, but the entire description is duplicated verbatim in German and English, roughly doubling length without adding information. The bilingual repetition is the main drag on structure.

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?

There is no output schema, so the description carries the return-value burden and does so: it explains content vs blocks, the package structure, and the specific error code with its payload. Combined with the pass-through instructions to order_send, an agent has enough to call and handle the result correctly; only edge behaviors like partial failures are unaddressed.

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 already 88%, so the baseline is 3, but the description adds a cross-parameter relationship the schema does not encode: a standalone form template with sendable:false/releaseBlocker:null requires coverTemplateId from a directly addressable letter template. Minor confusion arises because the description calls this input 'templateMergeValues' while the schema names it 'mergeValues'.

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: it fills the placeholders of a saved template with supplied values and returns subject/content or a complete cover-form package. It goes further by distinguishing the block-template case (returns finished blocks instead of content) and the standalone form case, which an agent can use to tell it apart from template_preview and template_get without opening schemas.

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 real workflow context: it names the downstream call (order_send) and specifies which values must be passed through unchanged, and it explains the coverTemplateId requirement for standalone form templates. It does not explicitly contrast with sibling tools such as template_preview or state when not to apply, which keeps it below a 5.

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