skill_record_ide_companion_evidence

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

With no annotations, the description carries the full burden. It discloses that it writes a JSON ledger, refreshes status, and returns path plus status, and explicitly negates two side effects (Tripo calls, Unreal mutation). This gives an agent a good sense of what the tool will and won't do. However, it does not mention failure modes, overwrite behavior, or required permissions, which keeps it from a 5.

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 compact, leading with the core action, then a one-line behavioral note, then a KB reference and example. It avoids fluff and front-loads the essential information. The only minor inefficiency is the repeated example line which could be trimmed, but overall it's well-structured.

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?

While the description gives a clear high-level purpose and an example, it does not cover the full parameter set or provide any detail on the output schema (which exists but is not shown). Given 9 parameters with no schema descriptions, the description is only partially complete. The KB reference might fill gaps, but the description itself is not fully self-sufficient.

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%, and the description provides no per-parameter explanations. The example shows session_plan, phase_name, and summary, but does not clarify the meaning or format of these or the other 6 parameters (e.g., artifacts, work_order, evidence_type). An agent would have to infer semantics from the example and names, which is insufficient for 9 parameters.

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 clearly states the verb 'Record phase evidence' and the resource 'durable local IDE companion ledger', and even specifies what it does not do (call Tripo or mutate Unreal). This distinguishes it from many sibling skill_* tools, which are about compiling dashboards, manifests, or sessions, not recording evidence.

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 provides an example and a KB reference, and implies usage when recording phase evidence. However, it does not explicitly state when to use this tool versus alternatives (e.g., skill_compile_ide_companion_dashboard), nor any conditions for not using it. The negative statement 'does not call Tripo or mutate Unreal' gives some contextual guidance but is not a clear usage directive.

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