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

Adds real value beyond annotations by clarifying the effect boundary: it does not release contact data or change resident permission, it only asks the team to arrange it. Annotations (non-destructive, idempotent, open-world) already cover safety and retry semantics, so the bar is lower; what remains unclear is the outcome of the request (approval flow, timing, failure modes).

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 front-loaded sentences with no filler: what it does, what it requires, and what it does not do. Dense domain jargon (SHARE_TENANT_CONTACT) is necessary, though the final clause is a slightly convoluted restatement of the read-back guidance.

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?

With an output schema present, return values need no explanation, and the description covers preconditions, effect scope and the follow-up read. The only material gap for a 5-required-parameter call is the absence of any hint about sessionToken or idempotency-key handling.

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%, so the description must carry the load. It recovers meaning for arrangementId ('one ... arrangement returned by get_details'), expectedVersion ('exact version') and confirmed ('explicit customer confirmation'), but says nothing about sessionToken or idempotencyKey beyond the vague idempotent hint.

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 ('Ask elron club to arrange the resident contact') and narrows it to exactly one SHARE_TENANT_CONTACT arrangement returned by viewings.get_details. This distinguishes it cleanly from siblings like viewings.get_details (read) and viewings.propose_availability.

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 are given: an owning verified inquiry, an arrangement ID from get_details with status SHARE_TENANT_CONTACT, the exact version, and explicit customer confirmation. It also names the alternative path — read get_details later for instructions actually released — so the agent knows when to read versus request.

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