Compare my turns

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context on top: it requires LLMxRay running, runs in under a second, calls no model, and reports what to move if either side has fewer than one turn. That dependency, latency and failure-mode disclosure goes well beyond the structured fields.

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 value proposition, then usage, then per-parameter guidance, then operational notes, with no filler sentences. It is dense and slightly long, but each block maps to a distinct decision the caller must make.

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?

No output schema exists, so the description carries the return-value burden and does so by enumerating the returned metrics and the verdict line. Prerequisites (LLMxRay), the error/degenerate case, and the filtering parameter are all covered, leaving nothing an agent needs to call this correctly.

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 baseline is 3, but the description adds interpretation the schema lacks: split_minutes_ago defines older turns as 'before' and newer as 'after' and tells the caller to set it to minutes since the change, and client is framed as 'your X-LLMxRay-Client name, so another tool's turns do not mix in'. This is meaningfully more than the schema's range/default/substring notes.

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?

Opens with the question it answers ('Did a change help?') and states the precise output: medians of cached share, prefill time, generation speed and prompt size for turns before and after a moment, plus difference and a cache verdict. It explicitly distinguishes itself from diagnose_my_turns and list_my_turns, so an agent can select it without opening any schema.

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 an explicit trigger ('after you changed a system prompt, keep_alive, num_ctx or the tool list') and names the two nearest alternatives with the condition that selects each: diagnose_my_turns for the finding that prompted the change, list_my_turns for the raw sequence. When-to-use and when-not-to-use are both covered.

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