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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior not in the annotations: rendered HTML is omitted, results are newest-first, and the underlying endpoint (GET /messages).

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?

A single dense sentence followed by two short clauses — front-loaded with what is returned, then the exclusion and ordering. The trailing 'GET /messages' is slightly extraneous but costs little.

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 no output schema, the description carries the return-value burden and discharges it by naming every returned field (subject, body, type, status, send_at, booking_id) and noting ordering and the HTML exclusion. An agent has enough to call it and interpret results.

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 60% with limit, offset and booking_id documented in-schema. The description reinforces which attributes exist and re-lists the type/status enum values, but adds no new syntax or semantics for the paging/filter parameters beyond what the schema already says.

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 ('List the e-mails and SMS Bookingmood sent or scheduled to guests') and enumerates the returned attributes, so an agent knows exactly what it gets. It is clearly distinct from siblings like list_bookings or list_invoices.

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?

Context is implied by the field list — an agent can infer this is the way to retrieve guest communications — but the description never states when to use it versus alternatives or any prerequisites. No sibling covers messages, so the gap is minor but real.

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