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

Annotations already establish read-only, idempotent, open-world, and non-destructive behavior, so the description's added value is high: it discloses exactly what is returned (textual trace, capsule_id, prior machine traces) and exactly what is never returned (private image bytes, visual claims). This gives an agent the behavioral profile needed without relying on inference.

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?

Two tight sentences: the first front-loads the core action and return contents, the second adds a necessary boundary. No filler or repetition of the annotations.

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?

Without an output schema, the description covers the return values, scope, and limitations. The single parameter is self-explanatory from schema plus description context, and the read-only safety profile is already captured by annotations, making this complete for the tool's complexity.

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?

With 0% schema description coverage, the description must compensate for the undocumented 'level' parameter, and it does by clarifying that the parameter selects one of 107 physical levels. It does not include a full parameter explanation, but for a single integer parameter bounded by the schema, this is sufficient semantic enrichment.

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 precise verb and resource: it returns the public textual trace for one physical level, plus capsule_id and prior machine traces. It also draws a clear boundary by explicitly excluding private image bytes and visual access, differentiating it from visual-consultation siblings.

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 makes the intended context clear: use this when you need the public textual trace and capsule_id for a level. The 'never returns private image bytes or claims visual access' warning implicitly discourages using it for visual/private data, though it stops short of naming an explicit alternative like prepare_visual_consultation.

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