ArcadeDB Multi-Model DBMS

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

With no annotations provided, the description carries full burden and does well by disclosing key behaviors: it stops the profiler, returns aggregated statistics (execution counts, timing details, plan costs), and saves results to disk for later retrieval. This covers mutation effects, output format, and side effects, though it lacks details like permissions or error conditions.

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?

The description is front-loaded with the core action ('Stop the query profiler and return the captured profiling data'), followed by supporting details in two efficient sentences. Every sentence adds value: the first states purpose, the second specifies output content, and the third notes disk persistence, with zero waste.

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?

Given no annotations and no output schema, the description provides good coverage for a 0-parameter tool: it explains what the tool does, what it returns, and side effects. However, it lacks explicit error handling or prerequisites (e.g., must have profiler running), leaving minor gaps in completeness.

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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately focuses on behavior rather than inputs, earning a baseline score of 4 for not adding unnecessary param details while compensating with clear action semantics.

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?

The description clearly states the tool's purpose with specific verbs ('stop', 'return') and resources ('query profiler', 'captured profiling data'), distinguishing it from sibling tools like profiler_start and profiler_status. It explicitly indicates this tool terminates profiling and retrieves results, unlike profiler_start which initiates it or profiler_status which checks its state.

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?

The description implies usage context by referencing 'captured profiling data', suggesting this tool should be used after profiler_start has been invoked. However, it does not explicitly state when not to use it (e.g., if profiler is not running) or name alternatives like profiler_status for checking without stopping, leaving some guidance gaps.

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