get_courier_kills

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the output as a list of courier kill events and details each field's semantics (e.g., 'game_time: Seconds since game start'), which gives the agent a clear picture of what to expect. It does not address edge cases like empty results or error behavior, but for a read-only query, the disclosure is quite solid.

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 well-organized with a summary line, bulleted output fields, and separate Args/Returns sections. It is mostly concise, though the 'Returns:' section at the end slightly duplicates the initial 'Returns a list of courier kill events' sentence, adding minor redundancy without detracting heavily from clarity.

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?

The tool is simple (one parameter, no nested output), and an output schema is present, so the description does not need to explain return structure in depth. It does provide field semantics and match_id context, making it complete enough for the tool's complexity. The main gap is the lack of guidance on when to choose this over related tools, but given the low complexity, this is acceptable.

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?

The input schema only specifies match_id as an integer with no description, so the description's 'match_id: The Dota 2 match ID' adds semantic meaning that the integer represents a Dota 2 match identifier. While minimal, this compensates for the 0% schema description coverage and is sufficient for the single parameter.

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's function with a specific verb and resource: 'Get all courier kills in a Dota 2 match.' It distinguishes itself from sibling tools like get_objective_kills or get_hero_deaths by focusing specifically on courier kills, and the detailed list of returned fields reinforces its unique purpose.

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 description provides clear context for when to use the tool: when you need courier kill events for a given Dota 2 match. It implicitly tells the agent to use this for courier-specific data, but it does not explicitly compare against alternatives like get_objective_kills or mention exclusions, so it stops short of a perfect score.

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