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

Annotations only say it is non-read-only, open-world and non-idempotent; the description goes much further, disclosing that it sends a REAL message to a real small business, that consent must be genuine, that contact details must never be invented, that content must be plain words with no links, and how to redirect urgent cases. That is exactly the context an agent needs before an irreversible outbound side effect.

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?

Front-loaded with purpose and exclusions before the constraints, and essentially every sentence carries a real rule (scope, consent, no invented details, no links, daily limit, urgent fallback). It is dense though — the consent/anti-fabrication rules run together in one long middle stretch rather than being broken out, which slightly hurts scannability.

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 an 8-parameter, fully documented, non-idempotent outbound tool with no output schema, the description covers scope, exclusions, consent, data-sourcing and rate limits. The remaining gap is what happens after submission (confirmation, expected callback timing, what the call returns), which an agent may want in order to set expectations.

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%, so the baseline is 3; the description earns above that by adding sourcing rules the schema does not state — 'never guess or invent contact details' and that the name and phone/email must be the person's own — which directly govern how name, phone, email and consent_to_contact get populated. It does not add format-level detail (e.g. ten-digit phone, 800-char details) beyond what the schema already documents.

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 Commercial Garage Doorman to contact a facility manager... about commercial or industrial doors') and enumerates the qualifying job types (repair, new building, replacement, maintenance program, dock equipment). No sibling tool (fetch, search, get_business_facts) could be mistaken for this, so differentiation is implicit but unambiguous.

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 when-to-use (commercial/industrial door work), when-not ('not for houses, and not for a door that is stuck open right now: that is a phone call'), and the alternative for the excluded case (call (905) 536-5369). It also states the precondition (the person clearly asked to be contacted and supplied their own name plus phone or email) and a rate limit of 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.