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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: each case is copied into an executable instance with its own status/remarks/one Configuration, and it exposes a precondition failure mode (mismatched run type, incomplete code generation, incompatible platform).

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-loads the core action and mode choice, and the TEST RUN INSTANCE definition earns its space because it clarifies the object model. The final sentence packs several constraints (milestones, folder, configuration, platform compatibility) into one dense clause, slightly hurting scanability.

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 12-parameter create tool with full schema coverage, the description covers run types, prerequisites, instance semantics, and configuration behavior well. With no output schema present, it stops short of describing what the call returns (e.g., the created run/instances), which is the remaining 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 coverage is 100%, so the baseline is 3. The description still adds value by explaining the configuration_id vs configuration_ids distinction (one Configuration shared by all instances vs case×configuration expansion) and the KaneAI platform-compatibility rule, neither of which is fully stated in the schema.

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?

Specific verb+resource ('Create a test run') with the two run modes and their semantic difference spelled out, plus a definition of what an included case becomes (a TEST RUN INSTANCE). No other sibling tool creates a run, so the agent can disambiguate from tm_create_test_case, tm_create_milestone, and tm_generate_test_cases immediately.

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 clear context and prerequisites: KaneAI runs only accept KaneAI-authored cases with completed code generation, manual runs only accept manual cases, and options are described as optional (milestones, folder, configuration). It never routes to a named alternative (e.g., when to use tm_generate_test_cases first), so it stops short of explicit when-not guidance.

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