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

Annotations already declare readOnly and idempotent, so the safety profile is covered. The description adds genuinely new behavior: result ordering, plan-based caps on limit, and the plan gate on resolved history — all things the agent could not see in annotations.

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, front-loaded with purpose and ordering before the plan constraints. The plan-limit detail partially duplicates the schema's limit description, a minor redundancy in otherwise tight prose.

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?

Output schema exists so return values need no explanation, and plan gating is disclosed. The one remaining gap is the relationship to the sibling get_vendor_incidents, which an agent would still have to guess at.

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 all three parameters are documented in structured form; the description largely restates the limit caps and only loosely gestures at timePeriod via 'plan window'. Baseline 3 is appropriate since the schema does the heavy lifting.

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 (get vendor incidents) plus scope (across all monitored vendors) and ordering (newest start first). It does not differentiate itself from the sibling get_vendor_incidents, leaving the agent to infer that the sibling handles per-vendor lookups.

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?

Plan-tier guidance is given (Guest/Free max 5, Standard+ can request resolved history), which frames eligibility context. However, there is no explicit 'use this instead of get_vendor_incidents when...' routing, so selection between siblings is only implied.

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