Repair network (bounded)

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

Annotations already signal readOnlyHint=false, destructiveHint=true, openWorldHint=true. The description goes beyond by detailing what destructive actions occur (resetting parameter expressions, re-enabling bypassed ops), the dry_run default that prevents changes, the hard bound max_steps, and the re-check/stop behavior. It also discloses the return object including rolled_back, providing a clear behavioral contract.

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 somewhat dense but well-structured: it front-loads the core purpose, then explains safety bounds, fix types, return values, and usage. Every sentence contributes value; however, it could be slightly tightened without losing critical details.

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 tool's complexity (autonomous repair, potentially destructive, multiple failure modes), the description covers all essential aspects: operation, bounding, dry_run behavior, safe vs risky fixes, error re-checking, return structure, and usage context. No output schema exists, so the return object explanation adds necessary completeness.

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 covers all three parameters with descriptions (100% coverage), so the baseline is 3. The description adds context about how dry_run and max_steps relate to the repair behavior, but it largely reinforces schema information without introducing new parameter semantics.

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+resource: 'Bounded, autonomous repair' that scans cook errors under a subtree, classifies, and plans a safe fix. It distinguishes from siblings by explicitly naming summarize_td_errors / get_td_node_errors for raw triage, making the tool's unique role clear.

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?

Provides explicit when-to-use guidance: 'Use it as the diagnostic "try the obvious safe fixes" loop after a build' and directs to alternatives for raw triage. It also explains the exclusion of risky cases (DAT syntax errors, missing inputs, unclassified errors) which are always PLAN-only, further clarifying appropriate usage.

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