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

Annotations declare readOnlyHint=false and destructiveHint=true, but the description reassures the agent this is “diagnosis only,” which reads as a safe, non-mutating operation. The reassuring “diagnosis only” framing directly conflicts with the destructive annotation, and the description never discloses what state the tool actually mutates. This is a misleading safety signal.

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?

Three tight sentences, front-loaded with the purpose and followed by return contents and scope. Every sentence carries information; minor room to tighten the return-value enumeration.

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?

With no output schema, the description appropriately summarizes the return shape (classification, next strategy, per-metric breakdown). The only meaningful gap is the failure to acknowledge the destructive/state-changing behavior declared by the annotations.

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 description coverage is 100%, so both parameters (processId, customerId) are already documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

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?

States a specific verb and resource (“Diagnose why an optimization failed to produce a winner”) and enumerates the concrete outputs (failure classification, next strategy, per-metric breakdown). An agent can distinguish it from the action siblings (trigger_optimization, stop_optimization, fix_worst_run) without opening any schema.

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 clear context for when to use it (after a failed optimization with no winner) and explicitly bounds the scope with “Does NOT trigger a restart — diagnosis only.” It does not name a specific alternative tool, so it stops short of full routing guidance.

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