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

Annotations only indicate readOnlyHint=false curved, but the description discloses the critical real-world side effect: it sends a real message to a small business. It also warns against guessing/inventing details, adds a per-day limit, and provides an urgent fallback, going well beyond the structured annotations.

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 description is four sentences long, front-loaded with the core purpose and then packed with necessary guardrails. No unnecessary fluff; each sentence adds crucial operational context (real message, consent, no inventions, one per day, urgent alternative).

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 tool with 8 parameters, no output schema, and limited annotations, the description covers all essential operational requirements: when to call, who to call for, what to include, what not to do, rate limit, and urgent-case fallback. There are no significant gaps that would leave an agent unsure how to invoke it safely.

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 100% (all 8 params documented), so the baseline is 3. The description adds extra semantic constraints not fully captured by the schema, such as requiring the customer's own contact detailschers, emphasizing 'Really sent' and the urgency fallback, which informs how parameters like phone and consent_to_contact should be valued. It does not repeat every param detail but reinforces the key correctness constraints.

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?

The description clearly states the action: asking Garage Doorman to contact a homeowner about specific services (repair, new door, opener, tune-up). It distinguishes itself from sibling tools like search and fetch by emphasizing that it sends a REAL message to a real small business, making the tool's purpose unmistakable.

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 provides explicit when-to-use conditions: only when the person has clearly asked to be contacted and has provided their own contact details. It also gives clear exclusions, such as urgent situations where the phone number should be given instead, plus rate limiting (one request per person per day).

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