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

With no annotations, the description carries the full burden of behavioral disclosure. It states the return format (ranked list of {failure_class, root_cause, fix_suggestion}) and implies a non-destructive read operation. It does not mention edge cases like empty results or ranking criteria, but the core behavior is transparent enough for an agent to call it safely.

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 sentences with zero waste. The critical 'BEFORE running' instruction is front-loaded, and the return structure is stated compactly. Every word contributes to the tool's purpose and usage.

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 read-only tool with three optional parameters and no output schema, the description provides the return structure, usage timing, and purpose. It does not explain how the optional parameters influence the ranking or what happens when no patterns match, but these are minor gaps. The description is sufficiently complete for an agent to decide when and how to invoke it.

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 coverage is 100%, so each parameter (tags, limit, agent_stack) is documented. The description does not add extra meaning beyond the schema; it only refers to 'agent setup', which loosely maps to agent_stack but without further detail. Baseline 3 is appropriate when the schema already handles parameter 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 uses a specific verb ('get') and resource ('known failure patterns for a given agent setup'), and explicitly frames the tool as a pre-execution step with 'BEFORE running'. This clearly differentiates it from reactive diagnostic siblings like diagnose_trace and diagnose_batch, which focus on post-hoc analysis.

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 gives explicit timing guidance: 'Call this before executing a plan and self-correct.' This is clear when-to-use advice. It does not explicitly mention alternatives or exclusions, but the 'BEFORE running' instruction and the sibling names (e.g., diagnose_*) make the intended context unambiguous. A small deduction for not naming an alternative directly.

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