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

Adds context beyond annotations: the message is irreversible ('cannot be recalled'), routes to a third party, produces an e-mail reply rather than an in-tool result, and that a repeat within 24 hours is deduplicated. The dedupe window is a mild tension with idempotentHint=false, but it reads as a server-side safety net rather than a contradiction of the destructive/outbound framing.

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?

Five dense sentences, front-loaded with what the tool does and immediately followed by the hard precondition and the alternative. Slightly redundant since the consent rule is restated from the schema, but 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?

For a 19-parameter outbound tool with no output schema, the description covers irreversibility, recipient, delivery channel, dedupe, and what the tool does not do. It stops short of saying what a successful call returns or how failures surface, which is the remaining gap.

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 100%, including per-field guidance like 'Never guess' the e-mail and the anti-spam website field, so the baseline is 3. The description reinforces the contact_consent gating workflow, but that rule is already spelled out in the schema, so it adds little beyond it.

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 — an outbound inquiry sent to the MERA team, delivered by e-mail reply to the given address. It also bounds scope by saying it does not book a date or confirm a price, which separates it from anything a reader might assume a 'quote' tool does.

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?

Explicit preconditions: call only after the person has seen exactly what will be sent and agreed to share name/e-mail with MERA (contact_consent=true). Names the preferred alternative (open_inquiry_form) and the condition that selects it ('when the host can show it'). Nothing is left to inference.

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