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

Goes well past the readOnly/idempotent annotations: discloses early-access gating (returns released false or not_released), that runs never send real mail, that a Last Price credential is required, and that sandbox self-registered keys get a 403 until the workspace is claimed. These are precisely the traits 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?

Purpose is front-loaded in the first sentence, followed by gating, safety, and auth prerequisites in short declarative clauses with no filler. The early-access sentence ('it answers released false or not_released') is slightly compressed and takes a reread, which costs it a point.

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 two-parameter read tool with rich annotations and no output schema, the description covers prerequisites, access gating, and side-effect safety. What the scenario result payload actually contains is only implied by 'every scenario's result', but nothing essential to calling it correctly 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 description coverage is 100%, so agent_id and run_id are already fully documented, including the constraint that an agent's own credential can name only its own agent. The description adds no parameter-level syntax or format detail beyond the schema, so the baseline 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 ('Read one behaviour test run for one of your agents') plus the returned scope ('with every scenario's result'). This clearly separates it from the list-shaped sibling get_agent_behaviour_tests and the mutating run_agent_behaviour_tests.

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?

'Read one ... run' signals the singular case versus the plural lister, and the credential/workspace prerequisites give context for when it will fail. It never names an alternative tool outright, so selection is implied rather than spelled out.

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