move_pattern_point

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

With no annotations, the description carries the full disclosure burden and does so strongly. It warns 'May change scene or write files', instructs 'Verify resulting state', and discloses that 'Geometry changes invalidate the old refs'. It also flags the critical uncertainty trait: 'A timed-out operation is UNKNOWN: reconcile_operation before any retry.' This is exactly the kind of behavioral context an agent needs beyond a bare mutation hint.

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 description is dense but every sentence contributes operational guidance, covering point selection, units, stale references, side effects, verification, and timeout semantics. It is front-loaded with the most important selection rule and contains no filler.

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 mutation tool with 5 optional parameters, no output schema, and no annotations, the description covers side effects, stale refs, and timeout handling very well. Yet it leaves the core action unstated and the relationship between point_index, pattern_index, and the 'legacy numeric form' under-specified. An agent could invoke it safely but not with complete confidence about parameter roles and expected 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?

The description adds meaning the schema lacks, such as 'x/y are 2D millimetres' and directing the agent to obtain point_ref from get_pattern_topology. However, it only vaguely refers to the 'legacy numeric form' without mapping it to point_index/pattern_index or explaining which parameters identify the target or whether any must be provided. With 0% schema coverage, the description only partially compensates for the opaque parameter list.

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 description never explicitly states the tool's core action—it does not say it 'moves' or 'updates' a pattern point. It implies geometry mutation through phrases like 'outer endpoints', 'straight polygons', and 'Geometry changes invalidate the old refs', but the main operation is left to inference from the tool name. This is a recognizable but unstated purpose.

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?

The description gives explicit guidance on invocation style: 'Prefer point_ref for verified outer endpoints, including curved boundaries. Legacy numeric form supports straight polygons.' It also sets a clear prerequisite ('obtain point_ref from get_pattern_topology') and timeout-specific follow-up ('reconcile_operation before any retry'). It does not, however, define when to choose this tool over an alternative editing tool, only which parameter form to prefer.

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