dump_collision_channels

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, but the description adds real context beyond them: it states it reads from GConfig [/Script/Engine.CollisionProfile] DefaultChannelResponses, i.e. config-derived and project-scoped rather than runtime state. It also declares the full return shape, which is unusual and helpful given no output schema.

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?

Front-loaded with the purpose in the first clause, then scope, read-only status, data source, and a compact field-by-field return listing. It is dense rather than bloated, though the long inline Returns enumeration is terse-to-the-point-of-run-on and could be more scannable.

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?

With no parameters, no output schema, and annotations already carrying the safety profile, the description covers what is needed: data source, scope (custom vs builtin counts), and all returned fields including nested channel objects. The one missing piece is disambiguation from the sibling list_collision_channels, whose name suggests overlapping behavior.

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 tool takes zero parameters, so the baseline is 4. The description instead spends its parameter budget explaining the semantic meaning of the values it produces (channel_value, query_type, query_index as 'the value a raycast/overlap passes'), which is the relevant analogue here.

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?

Specific verb ('dumps') plus resource ('this project's custom collision channels') and it enumerates the exact content of each entry (ECC_GameTraceChannelN -> name, trace vs object, TraceTypeQueryN index). The qualifier 'custom ... from config' implies a scope contrast with the builtin counts it reports, but it never names the near-identical sibling list_collision_channels, so the differentiation is only partial.

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?

Usage is only implied: '(the value a raycast/overlap passes)' hints that the query index is what you feed into traces/overlaps, which suggests when an agent would want this data. There is no explicit when-to-use, no when-not-to, and no routing to list_collision_channels, diff_collision_channels, or get_collision_profile, which an agent would plausibly confuse this with.

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