runtime_output

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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds the crucial behavioral fact that output is 'Drained on each call', i.e. a read that consumes state, plus the fact that entries carry call stacks and ZERO-BASED lines. It stops short of stating truncation limits, buffer caps, or what happens when no game is running.

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 sentences, front-loaded with the core action and the drain warning placed so it cannot be missed. Every clause carries information: the error taxonomy, the per-entry fields, and the consumption model.

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 output schema, the description correctly carries the return-shape burden by naming the fields of each error entry (file, function, line, call stack). It leaves open edge cases such as empty output, truncation, or behavior with no active session, which an agent polling this tool would want to know.

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 100%, so the wait and session_id semantics are already fully documented in the schema. The description adds nothing about either parameter (no guidance on wait values or multi-session selection), so the baseline 3 applies.

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 what a running game printed plus every structured error it reported, with enumerated error kinds. This is clearly distinct in spirit from debug_output and runtime_monitors, but the description never names a sibling, so the agent must infer the boundary from 'running game' alone.

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 implied by the drain semantics and the since-last-call window, which hints at polling for fresh output. There is no explicit statement of when to prefer this over debug_output or runtime_monitors, nor any exclusion, so the agent is left to infer context.

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