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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description's trailing 'Read-only.' is redundant with them. It does earn credit for behavior beyond the annotations: it discloses what is returned in each format (svg draws; json lists every cut element with its dimensions and host) and the non-obvious rule that a storey also draws parts held by its wholes, such as flights and roof slabs. With no output schema, that return-content disclosure is genuinely valuable.

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 content is front-loaded and dense with no filler sentences, but the pacing is run-on: a single colon-chained sentence crams kind, format, placement modes, and part-drawing behavior together. The parenthetical 'coverage.n_parts_via_whole' is opaque jargon that costs more to parse than it conveys. Restructuring into three short sentences would lose nothing.

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 9-parameter tool with a nested object and no output schema, the description covers the essentials: what each kind draws, what svg versus json yields, and how a section is positioned. The one notable gap is that refusal behavior for at_station lives only in the schema and the interaction between kind and the placement parameters is left to inference. Overall it is sufficient to call the tool 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 the schema already documents every parameter including the enums and the at_station sub-object, making 3 the baseline. The description adds one thing the schema cannot express: that the three placement conventions (axis+at_m, normal+through, at_station) are alternative ways to place the same cut rather than independent options. That is useful but modest, so it does not rise above baseline-plus.

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 opening clause names a specific verb and resource (cut/drawing) and enumerates the three kind values with concrete meanings: plan at a height, vertical section, and layers as three prism cuts along x, y, z. It also disambiguates 'layers' from material layers and points at get_element for those, which separates it from a real sibling. It falls short of 5 because it never contrasts with set_section or render_view, the two obvious neighbors an agent would hesitate between.

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?

Usage is only implied through the kind enumeration and the placement-mode sentence (axis + at_m, normal + through, or at_station). There is no explicit 'use this when you want a drawing rather than a section box' guidance naming set_section, render_view, or clip_elements as alternatives. An agent can infer the intent but must reason about it rather than read it.

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