List agent runs

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

Annotations already declare readOnlyHint=true and there is no contradiction. The description adds useful behavioral detail beyond the annotation: newest-first ordering, live-run indication, return fields, and the no-cost replay path. It does not discuss pagination or the meaning of 'live,' but this is reasonable for a read-only list tool.

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 with no filler. The core result (scene run index, ordering, live status, and return fields) is front-loaded, and the replay pointer is a useful, compact add-on.

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 one-parameter read-only listing tool with no output schema, the description is mostly complete: it names the fields returned and the ordering. The main gap is that scan_id's exact role is only implied, but this does not seriously impair an agent's ability to use the tool correctly.

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 0%, and the description does not explicitly say that scan_id is the scene identifier or describe its format. However, the phrase 'The scene's run index' strongly implies the single required parameter identifies the scene, so the parameter's purpose is partially inferred rather than fully documented.

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?

Title names the verb and resource ('List agent runs'), and the description sharpens it: a scene-scoped run index ordered newest-first plus live-run info. The reference to agent_replay as the replay mechanism distinguishes this listing tool from that sibling.

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 clearly implies 'use this to get the run list for a scene' and explicitly points to agent_replay for replaying persisted runs, giving an alternative. It does not explicitly exclude other run-related tools like agent_run_events, but the listing purpose is clear enough.

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