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

Beyond the annotations, it discloses the live effect that a running experiment will start serving the new price to its share of buyers, plus credential and workspace requirements including a 403 refusal for sandbox keys. This adds substantial operational context and does not contradict the declared non-readonly, non-idempotent, non-destructive behavior.

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 front-loaded with the core action and required parameters, then layers in constraints and auth requirements. Despite covering many constraints, every sentence contributes useful operational information without repetition.

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 mutation tool with no output schema, the description covers the critical missing context: live behavior, experiment constraints, credential requirements, and workspace claim requirements. An agent has enough information to decide whether and how to invoke it correctly.

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%, so the schema already documents all four parameters, including the label default and price meaning. The description reinforces required versus optional parameters but adds little parameter-level syntax or semantics beyond what the schema provides.

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 uses a specific verb and resource: 'Add one price arm to an existing experiment.' It clearly scopes the operation to existing experiments rather than creating experiments or allocating traffic generally, so an agent can distinguish it from siblings like create_experiment or allocate_variant_traffic.

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?

It explicitly states prerequisites and refusal conditions: the experiment must split traffic evenly, have room for another arm, reject weighted arms, and require a claimed Last Price credential and claimed workspace. These are concrete when-to-use and when-not-to-use signals rather than implied guidance.

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