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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds only an endpoint alias ('Same as POST /api/explain') and nothing about what the grade means, what the response contains, or any limits.

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 short sentences, front-loaded with the core purpose and no filler. The endpoint reference is useful shorthand, though jargon like 'score_v2' and 'delta_pct' is used without unpacking.

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 simple single-parameter read tool the annotations cover safety, but the description never explains what a 'score_v2 rubric grade' is or what the caller should pass as delta_pct, and no output schema exists to offload return-value detail. It is thin given the undefined parameter.

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 0%, so the description must compensate, but it merely repeats the parameter name 'delta_pct' without defining units, valid range, or what the delta is measured against. The lone number parameter is effectively undefined.

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 (explain) and resource (score_v2 rubric grade for a delta_pct), which is far beyond restating the name. However it gives no explicit differentiation from the sibling score_deal, leaving the agent to infer that this explains a grade while score_deal computes one.

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?

There is no indication of when to call this vs. score_deal, no prerequisites, and no relationship described (e.g., 'call after score_deal'). Usage is only implied by the tool name.

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