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

Goes well beyond the annotations by disclosing that a NEW immutable version is created, that the previous version remains fully reproducible, and that the response carries exact change-impact on median/quartiles/index. This adds meaningful mutation semantics (versioning/immutability) that destructiveHint alone does not 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?

Two tightly packed sentences with no waste; the operation and the required parameter are front-loaded before the versioning/return detail.

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-value explanation is unnecessary, and the description still notes the response carries change-impact. Versioning behavior, required param, and mutation nature are all covered; nothing critical for correct invocation 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 every parameter is already documented, so baseline 3 applies. The description only reinforces 'Pass benchmark_id' without adding format or interaction details (e.g., whether add and remove can be combined) beyond the schema.

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 specific verbs (add/remove members, rename) on a specific resource (custom benchmark), which clearly separates it from create_custom_benchmark, delete_custom_benchmark, and get_custom_benchmark. An agent can identify the operation without opening the schema.

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?

Implies use for modifying an existing benchmark and instructs passing benchmark_id, which distinguishes it from creation. It does not explicitly name sibling alternatives (create vs. delete) or state prerequisites such as who may mutate a benchmark, so it stops short of full when/when-not routing.

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