train_report

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

With no annotations provided, the description must carry the behavioral burden. It mentions that the report is archived to a specific path (data/dashboard/train-reports/) and includes markdown+JSON formats, which is useful. However, it doesn't disclose side effects like file overwrites or permission requirements, and the reference to GUIDE is vague. It doesn't contradict annotations (none exist), but leaves key behaviors undisclosed.

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 (one long sentence) but packed with technical references (GUIDE §4.3, data paths) that may be cryptic for an agent without context. It front-loads the main purpose but the structure could be clearer with separate sentences for components and behaviors. It earns a 3 as it is efficient but not optimally structured for parsing.

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 complex report-generation tool with 7 parameters including nested objects, the description covers the main content and mentions the output format and archive location. However, it lacks details on output structure (no output schema), return values, error handling, and the exact meaning of 'quantification fields' beyond the guide reference. The GUIDE references provide some context but are not self-contained.

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 description coverage is 100%, so all parameters have descriptions. The description adds context by linking quantification to GUIDE §4.3 and noting that artifacts are optional (derived from job record if absent). For baseline_eval, it explains degradation when omitted. These are meaningful additions, but the overall semantics are mostly covered by the schema, so a baseline of 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 clearly states the tool generates a training report with specific content components (data overview, config, eval comparison, artifact list, quantification). It is distinguishable from sibling tools like train_status or train_deliverable by focusing on full report generation. However, it doesn't explicitly contrast with siblings, and the resource is implied rather than stated as 'generate a training report'.

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 when a training report is needed after a training job. It references GUIDE sections, but does not explicitly state when to use this tool vs alternatives like train_deliverable or train_status. No exclusions or preferred alternatives are named, leaving some ambiguity.

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