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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context by clarifying the comparison is semantic rather than textual, which shapes how the agent should interpret results. It does not discuss determinism or what the diff output looks like, so it stops short of a 5.

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 with zero filler; the core purpose is front-loaded and the sibling routing follows immediately.

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?

No output schema exists, so the description should indicate what the diff yields (structured change list, summary, verdict) and clarify the context parameter's role. Annotations cover safety, but return shape and the undocumented third parameter leave real gaps for a comparison tool.

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 0%, so the description carries the full burden. It implies output_a/output_b are the two agent outputs being compared, but says nothing about the 'context' parameter or how it influences the diff, leaving one of three parameters entirely unexplained.

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+resource (semantic diff between two free-text agent outputs) and immediately disambiguates the type of diff with 'meaning-level change, not text-level'. It also names the siblings it is not, so an agent can distinguish it from forge_verify, drift_check, and detect_contradiction without opening schemas.

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 case is explicit (comparing two free-text agent outputs) and the exclusions are named with their conditions: forge_verify for build artifacts, drift_check for certified operational drift. That is a direct when-this / when-other routing rule.

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