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

Annotations already declare idempotent=true, destructiveHint=false, and readOnly=false, so the description doesn't need to restate the safety profile. It adds real behavioral information beyond that: the operation is a wholesale replacement (not a merge), and "Emails already made from it keep their own copy" scopes the blast radius by clarifying that existing sends are unaffected. It stops short of describing the response or permission requirements.

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 sentences, no filler. The verb+scope lands first, the prerequisite workflow second, and the side-effect caveat last — correct front-loading for an agent skimming tool lists.

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 6-required-parameter mutation with no output schema and no annotation-level nuance, the description covers the single biggest failure mode (accidentally blanking fields by omitting them). It's missing only parameter-level detail for template_id and preview_text and any note on what the call returns.

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 only 33% (only html and markdown are documented), so the description must carry weight. It names the four editable fields and implies every one must be resent, which is genuinely useful, but it never explains template_id, or that preview_text is nullable, or that html/markdown are mutually exclusive null-paired bodies. Partial compensation, not full.

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?

"Replace a template's name, subject, preview text and body, all at once" gives a specific verb (replace), a specific resource (template), and enumerates exactly which fields are affected. The full-replace semantics ('all at once') distinguishes it from any partial-patch sibling without needing to open the schema.

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?

It prescribes a concrete workflow: "read it with get_template first and send back what should stay," which tells the agent how to avoid clobbering fields. What it lacks is an explicit when-not or a pointer to create_template/delete_template as alternatives for adjacent intents, so it falls just short of the top mark.

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