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

Beyond the annotations, it discloses that model calls are billed to the workspace's own Anthropic key, that runs are capped at 20 per day, that early-access calls return released=false/not_released, and that runs never send real mail. These are exactly the operational and safety traits an agent cannot infer from readOnlyHint=false/openWorldHint=true.

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 core action is front-loaded in the first sentence and each subsequent sentence carries real information (billing, rate limit, parameter shortcuts, early-access flags, safety, prerequisites). The trailing requirement sentences are terse and slightly fragmented but not wasteful.

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 still indicates what comes back (the stored run with every scenario's result, plus the released flag in early access) and covers the access and billing prerequisites. The internal shape of each scenario result is left implicit, which is the only material gap.

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 every parameter is already documented, and the description only echoes scenario_ids and system_prompt_override without adding new syntax or constraints. It offers no extra guidance on private_terms, approved_recipients, or scenario_timeout_seconds, so the 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?

The first sentence gives a specific verb and resource: run behaviour test scenarios against an agent and return the stored run with each scenario's result. This clearly separates it from get_agent_behaviour_tests (which supplies the scenario ids) and from get_agent_behaviour_test_run, though it never names the retrieval sibling explicitly.

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 states concrete usage paths (pass scenario_ids to run a subset, system_prompt_override to test a draft prompt) and lays out preconditions: a Last Price credential and a claimed workspace, with a sandbox key refused with 403. It stops short of saying when not to use it, e.g. when to check readiness or existing runs first.

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