surface_trim

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

No annotations exist, so the description carries the full burden and does so well: it discloses unit handling, that multiple points in one cell collapse to a single removal, that cells are never addressed by index, that a failed trim changes nothing, and the exact INVALID_PARAMS reasons. Return payload keys are also enumerated.

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 the core action, then errors, returns, and a concrete example — a sensible ordering. A small amount of duplication with the schema (units default mm) and dense phrasing keep it from being a clean 5.

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?

Despite no output schema and no annotations, the description covers the prerequisite inspection step, the error contract, and the return shape, which is everything an agent needs to call this destructive geometry operation 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 all four parameters and the baseline is 3. The description adds genuine semantics beyond it — the point-per-cell addressing model, the dedup rule for multiple points, and the max_distance error consequence — though the units default restates the schema.

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 ("Trim surfaces with a tool") plus the secondary effect ("remove the cells nearest to the given points"). This clearly separates it from the sibling surface_trim_cells (which only inspects cells) and surface_untrim (which reverses the operation).

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?

Explicitly prescribes the workflow: "Call surface_trim_cells first to see the cells... then pass a point per cell to remove," naming the sibling tool and the prerequisite data. It also documents the failure conditions that route the agent back to inspection (point beyond max_distance, tool that cuts nothing).

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