List drift findings

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

With no annotations, the description carries the full transparency burden. It discloses behavioral details like ranking by severity and returning IDs, but does not explicitly state whether the operation is read-only or has side effects, nor mention pagination or limits beyond what the schema provides.

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 concise and front-loaded, with each sentence earning its place: it defines the resource, gives a ranking detail, specifies when to use it, and notes the return value. No fluff or redundancy.

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 the tool has 6 parameters and no output schema, the description provides sufficient context for a list operation: what it lists, how it's ranked, when to use it, and that it returns IDs for subsequent lookups. It does not detail the full response shape, but the mention of IDs is a key missing piece, making it reasonably complete.

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 description coverage is 83%, so the baseline is 3. The tool description adds conceptual context for the 'class' parameter by explaining drift vs. pattern in plain language, but the schema already provides similar detail for each parameter, so the description adds limited incremental value.

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 lists performance findings surfaced by sixty, distinguishing between regressions and standing problems. It also notes findings are ranked by severity and returns IDs, making its purpose unmistakable and differentiating it from siblings.

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 'Start here when asked to find or fix performance problems, N+1 queries, slow endpoints, or regressions,' providing clear when-to-use guidance. It also suggests passing returned IDs to get_finding, implying a workflow, though it lacks explicit when-not-to-use or alternative exclusion guidance.

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