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

Annotations already declare this as a safe, idempotent, read-only, open-world read, so the description does not need to restate safety. It does add behavioral value the annotations cannot: the tool spans two distinct datasets (agentic catalogue vs. complementary list) and reports SOTA/saturation/headroom fields, which tells the agent what the results contain. No disclosure gap of consequence.

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 with zero filler, front-loading the scope ('List every benchmark...') and ending on the actionable next step. Every clause earns its place.

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?

A single optional enum parameter, an output schema (so return values need not be described), and full annotation coverage. The description supplies scope, content, and the follow-up call — nothing an agent needs to invoke this correctly is missing.

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 100% and the enum values/omission behavior are documented in the schema, setting a baseline of 3. The description goes slightly beyond by mapping each enum option to substantive content ('agentic benchmarks' vs. 'vision, long context, factuality, instruction following, language'), which helps the agent decide whether to pass a `list` value at all.

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?

Uses a specific verb ('List every benchmark') plus the exact resource (the AI Agent Benchmarks catalogue and its complementary list), and enumerates the content dimensions covered (SOTA, saturation, headroom vs. vision, long context, factuality). It also names the downstream sibling get_benchmark, so an agent can separate this from the many other `list_*`/`get_*` pairs.

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?

Explicitly states the workflow: use this tool to find a benchmark slug, then call `get_benchmark`. That names the alternative and the condition that selects it, which is exactly what a discovery tool needs. No misleading or missing guidance.

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