create_sewing

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

With no annotations, the description carries the responsibility and does well: it discloses side effects ('May change scene or write files'), instructs to verify resulting state, and explicitly states that a timed-out operation is UNKNOWN with a reconciliation step. This is meaningful behavioral context beyond what structured data provides, though it omits details like permission requirements or rollback behavior.

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 carries weight: preferences, constraints, unsupported cases, prerequisites, side effects, and timeout behavior are all covered in a compact block. No filler or redundancy; critical safety information ('May change scene or write files') is included succinctly.

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 an 8-parameter tool with no schema descriptions, no annotations, and no output schema, the description covers several critical aspects (edge refs, ranges, directions, side effects, timeout semantics) but leaves gaps: pattern_a/pattern_b are unexplained, the return value/result format is not addressed, and 'fresh topology' is mentioned without detail. It is useful but not fully complete for a tool of this complexity.

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 0%, so the description must compensate. It does clarify side_a/side_b as edge refs with 0..1 ranges, directions, and legacy indices (likely line_a/line_b), but pattern_a/pattern_b are never explained, and the mapping between parameter names and described concepts is left implicit. Over half the parameters lack direct semantics.

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 tool name and context imply it creates a sewing, but the description never explicitly states the action or resource. It immediately jumps into usage guidance ('Prefer side_a/side_b edge refs...') without a clear 'Create a sewing between two edges' statement, leaving the agent to infer the core purpose from the name and sibling tools.

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?

Provides explicit and actionable guidance: prefer side_a/side_b refs, require explicit boolean directions, restrict to full-edge ranges [0,1], and warn that partial/free sewing is unverified. It also directs the agent to obtain refs from fresh topology and to use reconcile_operation before retry on timeout. However, it does not contrast this tool with alternatives like inspect_sewing or list_sewings for normal verification.

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