Get zones (room schedule)

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

Annotations already establish readOnly/idempotent/non-destructive/openWorld=false, so safety is covered. The description adds real behavioral context beyond that: the sort order, that totals are computed 'over ALL matching zones' (not just the page), what each include* flag actually returns, and that areas are post-reduction 'as in the stamp'. It lacks pagination/interaction notes (e.g. how limit/offset and totals interact), so not a 5.

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 purpose and output shape, then filters, then optional flags, with zero filler. The middle run-on sentence packing ~15 return fields is dense and could be bulleted, but every clause carries information.

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 full burden of describing the return value, and it does so by enumerating every emitted field, the appended totals, and the extra properties each include* flag adds. Combined with a complete schema, an agent has everything needed to call it correctly.

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 3 is the baseline, but the description genuinely enriches it: it enumerates the four filter axes (guids, stories, category, search text over name or number), specifies units (m², m, m³), and expands the include* flags far beyond their terse schema text ('walls/doors/windows surfaces, corners, extracted areas', 'boundary walls/beams, contained elements by type', 'area reductions with type/percent/area/polygon').

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+resource ('Lists zones (rooms) like a room schedule') and immediately characterizes the return shape and sort order (by story then number). It clearly distinguishes itself from the mutation siblings (create_zones/modify_zones/update_zones) and from get_element_details by scope.

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?

Names the alternative explicitly: 'For every setting of one zone use get_element_details', which routes the agent for the single-element case. It also frames the filtering dimensions up front, but gives no explicit 'when not to use' for the batch case or guidance on when the optional includes are worth the cost.

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