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

Annotations already declare the mutation profile (readOnly=false, destructive=true, idempotent=false), and the description adds genuinely non-obvious behavior: a NEW immutable version is created, the previous version remains fully reproducible, and the response reports change-impact on median/quartiles/index. It does not, however, mention authorization requirements or failure modes (e.g., invalid member ids).

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 sentences, each carrying distinct information (operation, side-effect semantics, return content, required param), with the core action front-loaded. No filler.

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?

With no output schema, the description usefully describes the return value and the versioning side effect, and it flags the required argument. It is nearly complete for a 4-param mutation tool, lacking only error/permission behavior.

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 only 25% (just benchmark_id), so the description must compensate; it maps the three intent parameters to their purpose (add/remove members, rename) and explicitly says to pass benchmark_id. The remaining gap is value format — it never says whether add/remove take member ids, names, or tokens.

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 (a custom benchmark), and its immutability/versioning framing clearly distinguishes it from create_custom_benchmark, get_custom_benchmark, and delete_custom_benchmark without the agent needing to open any 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?

Usage is implied rather than stated: requiring `benchmark_id` signals this operates on an existing benchmark (not creation), but there is no explicit when-to-use, when-not-to-use, or named alternative for editing vs. recreating vs. deleting. The agent can infer the niche but is not routed.

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