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

Annotations declare non-readonly, non-destructive, and non-open-world, but the description adds the substantive behavior: the owner replies directly to the buyer's email and no offer/contract is created, plus the hard prerequisite of explicit buyer consent to share name and email. That is real side-effect and PII-disclosure context beyond the annotations; the only gap is that it doesn't say what happens on failure or whether the buyer's email is verified.

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 sentences, each doing distinct work: what it does, what it is not, and the consent prerequisite. The negative scoping is front-loaded where it matters most for a mutation-adjacent tool.

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 9-parameter, non-idempotent send operation with an output schema, the description covers purpose, side effects, and the consent gate adequately. The remaining gap is the meaning of the required `id` and the optional contact fields, which the agent must infer from the schema alone.

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 only 22%, and the description compensates for the semantically load-bearing fields (buyer name, email, message, consent, the question-vs-viewing distinction). However, it says nothing about the required `id` (presumably the published home), `preferred_times`, or `buyer_phone`, which remain undocumented in both places.

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 and resource ("Forwards a question or viewing request ... to the owner of a published home") and explicitly bounds the action against the near-miss interpretations: it does not book a viewing and creates no offer or contract. An agent can tell exactly what this does without inspecting 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?

The description makes the use case clear (contacting an owner with a question or viewing ask) and rules out the tempting-but-wrong usage (treating it as a booking). It doesn't reference the sibling read tools, but those are search/retrieval tools with no realistic confusion, so the missing differentiation is minor.

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