recommend_failure_debug_next_steps

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

With no annotations, the description carries the behavioral burden, and it does so fairly well: it frames the tool as advisory ('recommend', 'suggests') rather than executing diff_sim_failure_results itself, and it discloses the output categories. It is silent on session state effects and no-failure edge cases, but these are less critical for an apparent read-only recommendation tool.

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?

Two tight sentences: the primary action and inputs are front-loaded, the output categories follow, and the diff_sim_failure_results suggestion is a single extra clause. No filler or repetition.

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 an analysis/recommendation tool with no output schema or annotations, the description gives enough high-level shape to make a reasonable call: required inputs are implied, and outputs are named. It leaves the exact response structure, the meaning of compile_log, and the form of the suggested diff_sim_failure_results call undefined, so an agent would still need to infer some integration details.

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 description adds meaning beyond the schema by relating log_path, wave_path, and top_hint to 'current log, waveform, and optional hierarchy', and the schema itself documents simulator as 'vcs / xcelium'. However, compile_log is never explained, so the 20% schema coverage is only partially compensated.

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 is specific: it chooses the highest-priority failure and recommends signals, instances, and suspected failure class, which goes well beyond the tool name. It also names the data sources (log, waveform, optional hierarchy) and the downstream diff_sim_failure_results suggestion. It does not explicitly contrast itself with overlapping siblings like analyze_failures or get_diagnostic_snapshot.

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 use context is implied rather than stated: 'current log, waveform' and 'on the next run' signal a post-simulation debugging stage. There is no explicit guidance about when to choose this tool over alternative analysis/debug tools, nor any exclusions.

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