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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: auth requirements, a specific error condition (403 for unclaimed self-registration workspaces), early-access degraded responses ('released false or not_released'), and a side-effect guarantee that runs never send real mail. That is real behavioral context an agent cannot get from the schema.

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?

Front-loaded with the purpose and the returned fields, then two short prerequisite sentences. The first sentence is a long comma-chained list, but every clause carries distinct information and nothing is redundant.

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?

There is no output schema, so enumerating the returned fields (release status, scenario pack, key connection, limits, recent runs) is exactly the compensating detail needed. Combined with the auth and 403 caveats, an agent has everything required to call this correctly and interpret the result.

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% and the single agent_id parameter is documented in the schema, including the UUID format and the credential-scoping rule. The description adds no parameter-level detail of its own, so 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?

A specific verb ('Read') plus resource ('behaviour tests') and the exact scope ('for one of your agents'), followed by an enumeration of what is returned: release status, scenario pack, Anthropic-key connection, limits, recent runs. It implicitly separates itself from get_agent_behaviour_test_run by covering 'recent runs' as a summary, but it never names that sibling or run_agent_behaviour_tests, so differentiation is inferential rather than explicit.

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?

Gives concrete preconditions for use: it needs a Last Price credential and a claimed workspace, and a sandbox key from self-registration is refused with 403. It also explains the early-access state where the answer is 'released false or not_released'. It does not explicitly point to run_agent_behaviour_tests for actually executing the tests, so the when-to-use vs. alternative is only implied.

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