get_metadata

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

With no annotations, the description carries the full burden and does disclose the important traits: bounded reads, truncation continuations to follow, cross-parameter preconditions for paging, and a safe-read/reconciliation rule. It omits auth or plan requirements and says nothing about error behavior or what a truncated response actually looks like.

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 purpose then constraints; nearly every clause carries a rule an agent needs. 'Follow truncation continuations' is dense to the point of jargon — it tells the agent to do something without saying what a continuation looks like.

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?

For a 7-parameter, no-annotations, no-output-schema tool this is close to sufficient: it establishes the read-only profile, the paging model, and the default return shape (pages and current page). The gap is the response envelope under truncation and the maxBytes/maxNodes budget interaction, neither documented here nor in an output schema.

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 coverage is only 43%, and the description compensates by adding real cross-parameter semantics absent from the schema: offset/limit page *direct children* and require nodeId with depth >= 1, plus the discovery-vs-full profile tradeoff. maxNodes and maxBytes (the two budget knobs) get no explanation in either the description or, for maxNodes, the schema.

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 and resource ('Read a bounded layer tree') and immediately names the cheaper mode ('prefer summary for discovery'). However, it never distinguishes itself from sibling tools like get_design_context, get_component_context or get_selection, so an agent must infer when this tree read beats those.

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?

Gives concrete selection rules: omit nodeId to get pages plus current page, use offset/limit to page direct children, prefer the summary profile for discovery, and the constraint that only unpaged/unprofiled reads can reconcile an uncertain write. It stops short of naming any alternative tool it competes with.

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