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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: no underlying Agentery data is touched and only a minimal audit record is retained. This refines what 'destructive' actually means here (soft-disable, not data loss), which is exactly the sort of disclosure the annotations cannot convey.

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?

Three short, front-loaded sentences: effect first, then the data-safety caveat, then the parameter. No wasted words, though the final 'Pass benchmark_id' sentence is largely redundant given the single required parameter.

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 one-parameter mutation with no output schema, the safety profile (annotations) plus the description's soft-delete clarification cover what an agent needs. Minor gaps remain around reversibility and permission requirements, but nothing blocking.

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% and the schema itself carries the useful 'cb_ token' format hint. The description's 'Pass `benchmark_id`' merely repeats the required parameter name without adding syntax or constraint detail, so the schema does the heavy lifting and baseline 3 applies.

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 ('Disable access to a custom benchmark') and, notably, clarifies that the delete is actually a soft-disable rather than a hard removal. This distinguishes it from what the name alone implies, though it does not explicitly contrast with siblings like update_custom_benchmark or get_custom_benchmark.

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?

No guidance on when to disable access versus updating or retrieving the benchmark, and no prerequisites or exclusions stated. Usage is only implied by the verb 'disable'. An agent gets no routing help among the custom-benchmark siblings.

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