surface_stitch

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

With no annotations, the description carries the full burden and does well: it discloses the default tolerance (0.1 mm), the is_solid success signal, the INVALID_PARAMS error cases, and the full return shape including removed_bodies. It stops short of explicitly stating that input surfaces are consumed into the result, leaving that to be inferred from 'removed_bodies'.

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 core action is front-loaded in the first sentence, followed by outcome handling and errors in a logical order. The return-structure sentence and the example are somewhat verbose but each carries usable information, so waste is minimal.

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?

No output schema and no annotations exist, and the description compensates by documenting the return payload, the solid-vs-surface outcome, default tolerance, and failure modes. An agent has everything needed to invoke it and interpret the result.

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 a 3 is the baseline; the description goes beyond by explaining that tolerance is the largest gap to close, that omitted means 0.1 mm, and that raising it resolves non-solid results. It also identifies where surface refs come from (inspect_query or earlier results), adding practical meaning beyond the schema text.

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 ('Stitch surface bodies / faces along shared edges into one body') and names the underlying Fusion feature, so the operation is unambiguous. The mention of is_solid and the surface_patch fallback differentiates it from surface-related siblings in the same list.

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 conditional guidance: if is_solid=false, raise tolerance or patch openings with surface_patch first, and lists the INVALID_PARAMS conditions (fewer than 2 distinct surfaces, join/cut). It does not explicitly contrast with sibling operations like surface_unstitch or body_combine, so selection guidance is strong but not exhaustive.

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