get_failed_work_items

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose that the tool returns the tail of each log, which is useful behavioral context beyond the schema. However, it does not mention whether this is a read-only operation, whether it triggers a cook, whether it only returns currently failed items or also historical failures, or what the response format looks like. The disclosed behavior is accurate but incomplete.

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 concise and front-loaded with the main purpose in the first sentence. The Args section is minimal and structured. It earns its place without excessive verbosity. The only minor issue is that the Args section adds little value beyond the schema, but the overall structure is clean 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 list-type tool with 2 parameters and no output schema, the description is moderately complete. It tells the agent what the tool does and what the main inputs are. However, it lacks information about the return structure (e.g., what fields are in each item, how logs are formatted), whether the list is sorted, and whether the tool has side effects like cooking. Given the absence of annotations and output schema, more context would be needed for an agent to fully understand the tool's behavior.

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 0%, so the description must compensate for the schema's lack of parameter documentation. The description mentions node_path and limit in the Args section, but only restates their names with minimal context: 'TOP node path' and 'Maximum items returned.' It does not explain what a TOP node path looks like, how limit interacts with pagination, or any constraints. This is a clear gap given the 0% coverage.

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 a specific verb and resource: 'List the work items that failed on a TOP node, with the tail of each log.' This clearly identifies the tool's function and distinguishes it from related siblings like get_work_item_states or get_top_logs. It could be slightly stronger by explicitly naming a sibling alternative, but the core purpose is unambiguous.

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 implies usage context: it is for inspecting failed work items on a TOP node, which is a debugging/error-investigation scenario. However, it does not explicitly state when to use this tool versus alternatives like get_work_item_states, get_work_item_info, or get_top_logs. The context is clear enough for an agent to infer the primary use case, but exclusions and alternatives are not named.

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