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

Goes meaningfully beyond annotations: discloses the side effect that an existing receipt email may be sent, the token-only constraint for resident support, and the retry contract for idempotencyKey, which complements idempotentHint=true. It stops short of stating what a successful submission produces or what happens if a token is invalid or expired.

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?

Four tight sentences with no filler, and the highest-value constraint (idempotencyKey reuse on retry) is placed last as an explicit warning. Slightly dense sentence-packing in the second sentence costs it a point.

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?

An output schema exists, so return values needn't be explained, and the side-effect and retry behavior are covered. But for a 13-parameter, 6-required mutation with zero schema descriptions, the absence of per-category field requirements leaves an agent guessing at correct invocation.

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 0% across 13 parameters, so the description must carry the burden and does not. It adds meaning only for category, idempotencyKey and photoUploadTokens; name, email, message, confirmed, locale, companyName, apartmentCount, desiredMoveInDate and apartmentOfInterest are entirely unexplained, and there is no guidance on which fields each category requires.

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?

Specific verb ('Send') plus four precisely named request types that map one-to-one onto the category enum. It also disambiguates from the sibling contact.upload_photo by explaining that tokens come from there, so an agent can route without opening either 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?

The four enumerated categories give clear selection context, and the resident-support clause implies a boundary (photo tokens only, no tenancy record access). However, it never states what to do instead when a request falls outside this public intake, e.g. which sibling handles applications or viewings flows.

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