get_failed_tasks

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It states the tool shows failed tasks and log file names, which implies a read-only operation, but it does not explicitly say so. It adds useful context by naming specific key logs, which helps the agent know what to expect. However, it does not mention any side effects, permissions, or limitations. For a simple get operation, this is adequate but not comprehensive.

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 concise sentences with no redundancy. The primary purpose is front-loaded in the first sentence, and the second sentence adds a specific, useful detail about key logs. Every word earns its place, and there is no jargon or fluff.

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?

Given the simplicity of the tool (one parameter) and the presence of an output schema (not shown but referenced), the description is mostly complete. It explains the scope (failed tasks) and the availability of log files, which is the key output. The mention of specific log names helps the agent understand the return format. However, it does not describe how to use the log files (e.g., download them via download_log), but that is outside the tool's direct scope. Minor improvements could include clarifying that the output includes log file names for further retrieval.

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?

The schema has one required parameter, build_id, with no description and 0% schema description coverage. The tool description does not mention build_id at all, providing no additional meaning beyond the parameter name and type. The agent is left to infer that it is the identifier for the build whose failed tasks are being retrieved. This is a significant gap given the lack of schema documentation.

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 clearly states the tool's purpose: 'Get failed tasks for a build with their available log files.' It specifies the resource (failed tasks) and the action (get), and clarifies that it only shows failed tasks along with log file names. This distinguishes it from siblings like list_build_logs or search_log, which are broader or different in focus.

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 the tool is used to retrieve failed tasks and their logs, which is a specific debugging scenario. It even highlights 'Key logs for debugging: mock_build, mock_stderr, mock_root,' suggesting it's for debugging failed builds. However, it does not explicitly state when to use it instead of alternatives like list_build_logs or search_log, nor does it mention exclusions. The guidance is clear in context but not fully explicit.

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