get_execution_report

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

With no annotations, the description carries the full burden. It discloses that the operation is read-only ('Read'), the data source (listener output), and that it can be called on running executions. It does not mention potential side effects, latency, or error handling for invalid IDs, but for a read operation this is acceptable. It adds context about the metrics but not deeper behavioral details like caching or consistency.

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 a single, information-dense sentence that front-loads the core purpose and immediately lists the output metrics. Every word contributes value; there is no fluff or repetition. It is concise without losing specificity.

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 tool with one parameter and no output schema, the description covers the essential elements: what it does, when it can be used (finished or running), and exactly which metrics it returns. The lack of an output schema is mitigated by the metrics list. It does not mention error conditions or return formatting, but that is a minor gap given the simplicity of the tool.

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 schema has a single parameter, executionId, with 0% description coverage. The tool description does not explicitly explain what the parameter means beyond its name—it only says the tool retrieves results for 'an execution', but does not reiterate that executionId must be the ID of the execution whose report is desired. Since schema coverage is zero and the description fails to compensate, the parameter semantics are under-specified.

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 uses a specific verb ('Read and aggregate') with a clear resource ('results of a finished (or still-running) execution') and enumerates the exact metrics returned (per-label and overall count, error rate, latency percentiles, throughput, KB/sec). It distinguishes itself from siblings like get_execution_status by focusing on detailed report data from listener output.

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 states the tool works on finished or still-running executions and specifies the source (Aggregate Report / Summary Report listener output), giving context for when it applies. However, it does not explicitly contrast it with siblings like get_execution_status, nor does it state when NOT to use it (e.g., for just checking status). Usage is implied but not fully explicit.

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