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

Annotations already flag destructiveHint=true and idempotentHint=true; the description adds real context by disclosing the validation rules (unknown variables, missing/duplicate required slots, unsupported classes are rejected) and that theme/company data is injected at send time, not saved. It does not mention that unspecified nodes may be overwritten, which would be the one gap.

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: the action, the validation/rejection semantics, and the downstream preview pointer. Front-loaded with the verb and 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?

Covers the mutation modes, validation behavior, deferred injection, and the verification path, which is strong for a 6-param nested write with no output schema. The only omission is what happens to existing node maps when only subject/preheader are passed.

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 the description need not restate parameter docs, and it doesn't. It adds only the implicit linkage that nodes is a 'full flat node map' and reset is the alternate mode – already conveyed by the schema. Baseline 3 applies.

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+resource ('Save a site email's subject, preheader and/or full flat node map') and enumerates the fields being mutated, plus the reset escape hatch. It names a sibling (preview_site_email) so the agent can distinguish save from render.

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?

Clearly frames the two modes (save fields vs. reset: true) and points to preview_site_email for verification. It never states when to choose this over get_site_email/list_site_emails, but the write-vs-read intent is unambiguous.

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