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

Goes well past the annotations: it discloses the side effect ('queues a business email'), the exact idempotency contract (new random 16–100 char key, identical retries return the same receipt, changed input under the same key is rejected), and the return surface ('only a receipt, never customer data or credentials'). Those details explain what the destructiveHint/openWorldHint write actually does and what it will not return.

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-loads the core action and recipient before the conditions, and almost every clause carries information (authorisation, idempotency, side effect, receipt). It is a single dense run-on paragraph, so structure is weaker than the content density deserves.

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 write tool with no output schema and a deeply nested payload, the description covers prerequisites, side effects, retry semantics, the return value and the production restriction. An agent can decide whether to call it and how to retry correctly without further sources.

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 0% and the payload nests 12 required fields, so the description must carry the load — and it does add real constraints absent from the schema: the 16–100 character idempotency key (the schema declares no length), the Vienna 1010–1230 postal range, and the 'current privacy version' requirement. It leaves field-level meaning for work_type, preferred_time format and the consent booleans implicit.

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 — 'Creates a private home, office or building cleaning enquiry' — plus the named recipient (Sauber mit Sam / Samiha Aktaa), the channel (office@sauber-mit-sam.at) and the geographic scope (Vienna 1010–1230). That is enough to separate it from submit_direct_installation_inquiry and the find_* discovery siblings without opening any 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?

Gives clear conditions for use: explicit customer authorisation for the exact details, named recipient and current privacy version, and 'production accepts real customer enquiries only'. It also carves out what the tool is not (no booking, quote, payment, public posting, contact resale). It never names a sibling or says 'use X instead', so it stops short of full alternative routing.

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