platform_eval_runs

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

With no annotations, the description carries full responsibility for disclosing side effects, prerequisites, or safety. It lists actions like create, update, cancel, start (mutations) but does not describe potential impacts, auth requirements, or reversibility. The generic statement about 'generates, runs, reads' does not cover operational behavior.

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 two sentences, front-loaded with context, and the action list is compact. No fluff, but the long action list could be better structured (e.g., grouped by type). Still, it's concise and efficient.

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 multi-action tool with 12 actions, nested params, and no output schema, the description is incomplete. It doesn't explain what each action does, expected return values, or practical usage. An agent would need to infer behavior from action names and schema alone, which is risky for complex operations.

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 83% and each parameter already has meaningful descriptions (e.g., runIds: 'Exactly two run IDs for compare. Prefer this over query.runIds.'). The description only repeats the action enum without adding semantics. It barely adds value beyond the schema, so a baseline 3 is appropriate.

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 states the tool manages eval runs for ABL repair loops, which is a specific verb-resource pair. It also provides context about Arch generating eval assets and reading CI evidence. However, it doesn't explicitly differentiate from sibling tools like platform_eval_sets or platform_eval_scenarios, so it's clear but not strongly distinctive.

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 no explicit guidance on when to use this tool versus alternatives. It only says 'manage eval runs' without indicating scenarios or exclusions. Given multiple eval-related siblings, the agent has no cues for selection.

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