get_trace_delta

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

Annotations declare readOnlyHint and idempotentHint, ensuring safe and repeatable calls. The description adds context beyond annotations: working in any state and explaining cursor alternatives (mark_trace_cursor or raw timestamp). No contradictions.

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 extremely concise: one line for purpose, one line for state, and three lines for parameters. Every sentence adds value with 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?

Missing output schema, so description should explain what gets returned (e.g., format of log entries). It does not describe the return value or error conditions. With only 3 parameters and simple behavior, the absence of output details makes it marginally 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 coverage is 0%, but the description compensates fully: cursor is explained as 'Cursor returned by mark_trace_cursor or a raw monotonic timestamp', limit as 'Maximum number of entries to return', and tracepoint_id as 'Optional tracepoint filter overriding the cursor filter'. This adds critical meaning beyond the schema's type definitions.

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 verb 'Get' and the resource 'tracepoint log entries' with the mechanism 'after a cursor'. It distinguishes from sibling tools like get_trace_log (which returns full log) and mark_trace_cursor (which creates cursors).

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 mentions 'State: Works in any state' but does not explicitly state when to use this tool over alternatives like get_trace_log. The cursor parameter implies prior use of mark_trace_cursor but lacks explicit guidance.

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