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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the trailing 'Read-only.' largely restates structured data. What the description does add beyond the annotations is the shape of the payload: per-test prompt+expectation and the latest run's summary, which matters because there is no output 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?

A single front-loaded sentence carries the resource, its scope, the item shape, and the returned summary, with a two-word safety tag at the end. 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?

For a one-parameter read tool with no output schema, the description covers what is returned (tests plus latest run summary) and the safety profile. Missing are ordering/empty-state/pagination hints, which are minor for this simple list operation.

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 coverage is 100% and agent_id is fully documented in the schema, including where the id comes from (list_agents / create_agent / get_catalog). The description adds nothing about the parameter, 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?

States a specific verb (List) and resource (the agent's saved test suite), and the parenthetical defines what a test is (prompt plus deterministic expectation), which separates it from save_test and run_tests. It stops short of explicitly saying it does not execute tests, so the differentiation from run_tests is implied rather than stated.

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?

There is no when-to-use guidance and no named alternative. An agent must infer on its own that run_tests is the tool to call when it actually wants to execute the suite rather than view it, and that save_test is how tests get created.

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