zins_get_cyber_incidents_by_location

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'Read-only analytics.' It adds behavioral details beyond annotations: the output format (id/name/total per row) and a critical constraint (window must be 7- or 14-day interval). It does not specify auth requirements or rate limits, but given the read-only nature, the added context is sufficient.

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?

The description is three sentences, immediately names the purpose and key constraints, and contains no fluff. It is well-structured and front-loaded.

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 7-parameter analytics tool with no output schema, the description covers the core grouping dimension, output row format, and time-window restriction. It omits details like how limit works or the distinction between absolute timestamps and relative days, but the essential usage context is present. A score of 4 acknowledges it is useful but not exhaustive.

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 only 14% (only 'query' has a description). The description partially compensates by explaining that grouping can be by location or app/user/department (addressing 'categorize_by') and that the window must be 7- or 14-day (hinting at time parameters). However, it does not explain the meaning of limit, start_time/end_time vs days_ago, or how they relate. The description adds some value but does not fully fill the gap left by low schema coverage.

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 clearly states the tool gets cyber-security incidents grouped by location (or app/user/department), specifies it produces one id/name/total row per location, and mentions it's read-only analytics. This distinguishes it from sibling tools like zins_get_cyber_incidents (which likely doesn't group by location) and gives a concrete function.

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 guidance on when to use it ('useful for ranking which sites carry the most incidents') and imposes a constraint (window must be 7- or 14-day interval). It does not explicitly name alternatives or state when not to use it, but the use case is clear enough. Sibling tools like zins_get_cyber_incidents_daily might be more appropriate for daily trends, but that's not mentioned.

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