scl_check_goose_bindings

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

There are no annotations provided, so the description carries the full behavioral disclosure burden. It does well by disclosing the 'subtle one' — the dataset-carried-signal check — which is the tool's distinguishing behavioral trait. It also explains the input-file restriction (must contain all IEDs, .scd not .cid). It doesn't state return format, but an output schema exists (context signals confirm), so that burden is partially lifted.

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?

Three compact paragraphs, each earning its place: the first defines the tool and its failure categories, the second enumerates the four report types, and the third provides the essential input-file prerequisite. Zero filler, every sentence adds distinct value, and critical constraints are front-loaded.

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?

This is a moderately complex analysis tool with one well-explained input and an output schema present. The description thoroughly covers what the tool checks and the file prerequisite. Minor gaps: no mention of whether the tool also reports matched/healthy bindings, and no guidance on output size or interpretation, but the output schema and the explicit failure-category enumeration make this largely 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 for the single 'path' parameter. It does state the file must be an .scd containing all IEDs and that a .cid won't work, which adds meaning to 'path' beyond the bare string type. However, it doesn't mention format expectations (e.g., relative vs. absolute paths) or error behavior if the file isn't an SCD. Given only one parameter, the added file-type guidance is helpful but could be more explicit.

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 uses a specific, concrete phrasing: 'Trace GOOSE publishers to subscribers and flag every way the binding can be broken.' It enumerates the exact categories of failures reported (unsubscribed publishers, missing network addresses, nonexistent IEDs/control blocks, dataset-signal mismatches). It clearly distinguishes itself from sibling tools by going beyond simple listing (scl_list_goose) or validation (scl_validate) into cross-IED binding analysis.

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 explicitly states when this tool is appropriate: it requires a multi-IED .scd file because bindings are cross-IED, and explicitly notes that a single-IED .cid cannot show them. This gives clear guidance on the file prerequisite that separates it from tools operating on single-file input, effectively directing the agent to use this only when multiple IEDs are involved.

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