Update email draft

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the critical detail that "blocks replaces all blocks" and explains how to preserve existing blocks with keep + id from postfjord_get_campaign — exactly the disclosure an agent needs before triggering a destructive overwrite. It also discloses the draft-only state constraint, which no annotation conveys.

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 mutation scope and the "only send what changes" rule, then the block-replacement warning, then the state preconditions. The middle is dense and slightly telegraphic ("A block written back with its id stays in its background box"), but nearly every sentence carries operational meaning.

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 destructive, 8-parameter mutation with no output schema, the description covers the state precondition, the audience selector rules, and the destructive block-replacement semantics. Minor gaps remain: it doesn't say what the call returns or whether unchanged fields are echoed back, but nothing essential to invoking it correctly is missing.

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 low (38%) at the top level, and the description compensates for the riskiest fields: the audience is "tags (tag names), segment (a saved segment) or everyone: true, one of the three" — a mutual-exclusivity rule the schema does not state — and the keep/block-id round-trip semantics. It does not clarify campaignId, name, subject or preheader, but those are largely self-evident from 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?

Opens with a specific verb and resource ("Changes the subject, preheader, name, blocks or audience of a draft email") and enumerates exactly which fields are mutable, so an agent can immediately tell this is a partial-update tool for drafts rather than a create/publish tool. It also names the sibling postfjord_cancel_campaign for the scheduled case, which separates it from the surrounding campaign siblings.

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 the partial-update rule up front ("only send what changes"), states the hard precondition ("Only a draft can change"), and names the exact alternative workflow for the blocked case ("a scheduled email must be unscheduled first with postfjord_cancel_campaign"). It even carves out an out-of-scope case ("Automation emails are changed in the app"), so both when-to-use and when-not-to-use are explicit.

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