Spr insert fitting

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

Annotations already declare this as a non-read-only, non-destructive, non-idempotent, closed-world mutation, so the description only needs to add context — and it does: a new intermediate/junction node is created, the pipe is split at a normalized position, and the resulting node id must be retrieved from spr_list_summary. It does not say whether the original pipe object is replaced or segmented, which is the one remaining behavioral gap for a topology-mutating tool.

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?

Dense but well front-loaded: the core action comes first, then a per-fitting-family breakdown, then the node-id retrieval hint. The trailing bracketed rule reference is a bit tacked-on but carries actionable routing information (bulc_knowledge_search).

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 exists, so the description compensates by telling the agent where the new node id surfaces (spr_list_summary). Combined with 100% schema coverage and explicit annotations, an agent has enough to invoke it correctly; only failure modes (invalid pipeId, off-range position) are unaddressed.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema: it disambiguates l_x/l_y ('go along X first' vs 'Y first'), explains that elbow45 turns the last leg into a 45° diagonal, and scopes which fitting values consume `position`. downstream_diameter semantics remain entirely schema-supplied.

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+resource ('Insert a fitting into an existing pipe') and then decomposes the operation by fitting family, so an agent knows exactly what each enum value produces (L-bend corner node vs. split junction node). This distinguishes it from spr_add_pipe, which is named as the complement rather than a competitor.

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?

Clear context: which fitting values route through a new intermediate corner node versus splitting at `position`, and it explicitly hands off to spr_add_pipe for drawing branch pipes. It also explains the junction special case (plain split, fitting auto-detected). It stops short of stating when NOT to use this tool or naming an alternative for removing/undoing a fitting.

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