get_latency_regressions

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

With no annotations, the description adds some behavioral context by explaining the data source ('persisted storage') and filtering. However, it does not disclose other traits like read-only nature, rate limits, or performance implications, which are important for a read operation.

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 two sentences, each serving a clear purpose: first defines the output, second provides usage guidance and sibling context. No fluff, well front-loaded.

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?

The description lacks details about the output format or fields, which is critical since there is no output schema. Parameters are covered, but the return value is vague ('detected latency regressions' without structure), leaving the agent uncertain about the response.

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 100% description coverage, so the schema already documents each parameter. The description adds no further meaning beyond the schema, earning the baseline score of 3.

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 retrieves 'latency regressions' defined as sustained p99 command-latency degradations. It distinguishes itself from the sibling 'get_anomalies' by noting it is pre-filtered to regressions, providing a specific verb and resource.

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 explicitly says to use this tool when investigating 'the database got slower' and positions it as a companion to 'get_anomalies', implying a narrower use case. It provides clear context but does not explicitly state when not to use it.

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