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

Despite annotations already declaring destructiveHint=true and idempotentHint=true, the description adds substantial non-obvious behavioral detail: `fromEmail` is read-only and requires dashboard domain verification, `fromName`/`replyToEmail` reject null, `invite`/transactional `isEnabled` toggles and `layoutMode` are read-only, arrays replace wholesale, and INLINE layout bodies must include `{{emailFooter}}`. This is exactly the kind of constraint info an agent cannot get from annotations or schema.

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 purpose is front-loaded in the first clause, followed by constraint sentences that each carry distinct information. It is dense rather than padded, though the single long paragraph mixes several constraint families and could be marginally better organized for scanning.

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, idempotent, nested-object patch tool with an output schema (so return values need no explanation), the description covers the read-only traps, null handling, array replacement, conditional template tokens, and target resolution. An agent has everything needed to invoke it 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?

With only 50% schema description coverage, the description compensates well: it clarifies which nested fields are writable vs read-only, null-vs-omit behavior for sender fields ('Omit either field to keep its current value, including an unset value returned by a read'), conditional body requirements, and the campaignId default. This meaningfully exceeds what the schema conveys.

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+scope: 'Update writable Emails tab fields for your GrowSurf program under `fields`'. An agent immediately knows this is a patch operation on the emails configuration. It does not explicitly name its read counterpart (growsurf_get_campaign_emails) or otherwise route among siblings, so it falls short of a 5.

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 provides operational context (targets `campaignId` if supplied, otherwise `GROWSURF_CAMPAIGN_ID`) and explains omission/retention semantics, which is useful guidance. However, it never states when to reach for this tool versus alternatives like `growsurf_get_campaign_emails` or `growsurf_update_campaign_options`, leaving usage largely implied.

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