make_rod_pocket

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does a good job: it walks through the operation sequence (adds a pocket strip, sews it, holds the panel, places a rod, lets the panel hang), discloses a known limitation ('the pocket can be fuller in places'), and tells the agent to verify with capture_3d. It also notes the CLO 2025.2 verification and the pocket_side reliability caveat. It doesn't explicitly state that the operation is destructive or irreversible, but the 'Save a checkpoint first' instruction implies mutation and risk, which is meaningful behavioral context.

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 well-organized: a first paragraph for what it does and when to use it, a second paragraph for the operation sequence and verification advice, then a compact Args block. Every sentence earns its place; the only minor inefficiency is some redundancy between the first paragraph's 'hang the panel on a rod' and the second paragraph's step-by-step hanging description, but that repetition serves both purpose clarity and behavioral transparency.

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 complex 6-parameter tool with no annotations and no output schema, the description is remarkably complete: it covers prerequisites, the physical process, known failure modes, verification steps, and parameter semantics. The main gap is that it doesn't describe the return value in detail beyond 'Returns whether the cloth stays up at the ends and in the middle' — but since there is no output schema, a bit more precision on the return format (e.g., booleans vs a status object) would have made it fully complete.

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 description coverage is 0%, so the description must compensate, and it does. It explains pattern_index can be a single panel or a list of panels sharing one rod and adds the constraint that their top edges must be at the same height. It gives physical meaning to pocket_depth ('Height of the pocket strip in mm (the tube is roughly 1.4x this around)') and clarifies pocket_side with a concrete reliability caveat ('Only front (+z, towards the front camera) forms reliably in CLO 2025.2') plus a workaround. rod_diameter, rod_overhang, and settle_steps are only restated with units, which is modest, but the overall parameter coverage is strong.

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 opens with a specific verb and resource: 'Make a rod pocket along a panel's top edge and hang the panel on a rod (curtains, banners, flags).' It clearly distinguishes the tool from the sibling hang_on_rod by explaining that this tool both creates the pocket and hangs the panel, and it names the sibling explicitly. The scope (single panel vs several panels) is also stated, so an agent can tell this apart from hang_on_rod without opening the schema.

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 when-to-use and when-not-to-use guidance: 'Verified with one panel; with several panels a pocket often fails to wrap, so prefer hang_on_rod there.' It also states the prerequisite that the panel needs a straight, horizontal top edge, and advises saving a checkpoint first. This is exactly the kind of routing and precondition information an agent needs.

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