tracesHitList

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

Given readOnlyHint=true and destructiveHint=false, the safety profile is already covered by annotations. The description adds meaningful behavioral context beyond annotations: the response can be very large for a single ADT call and is therefore capped, and heaviestFirst controls which end of the list is retained. This helps an agent understand output size and ordering behavior.

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?

Two tight sentences with no filler. The first sentence establishes the resource and value; the second warns about size and directs attention to the key parameter. Every clause earns its place.

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 plus schema is sufficient for an agent to call it correctly: id is sourced from tracesList, limit caps results, heaviestFirst controls sorting, and withSystemEvents is self-explanatory. There is no output schema, so the description's 'what was called how often and for how long' provides the return semantics, though it stops short of describing the exact shape of the returned entries.

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 100%, so the schema already documents all four parameters. The description adds a little context around heaviestFirst by calling it 'the expensive end' and clarifies the cap rationale, but it doesn't materially extend the meaning of id, limit, or withSystemEvents beyond what the schema already states.

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 is clear that this tool returns the hit list of a specific trace — 'what was called how often and for how long' — and positions it as a performance overview. It doesn't use an explicit verb like 'get' or 'list', and it doesn't name sibling tools to distinguish itself, but the resource and intent are unmistakable.

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 gives a clear use case ('the fastest read of where the time went') and practical guidance to pass heaviestFirst when the expensive end is wanted. It doesn't explicitly contrast with sibling trace tools like tracesStatements or tracesList, but the context and parameters make the intended usage evident.

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