Read Recorded Tool Calls from a Session

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds value beyond them by disclosing the record shape ({ seq, at, tool, input, result?|error?, elapsedMs, clientId?, sessionId }), that it reflects 'exactly what the invoker saw', and phase/cost/output semantics. It still omits capacity/pagination behavior at the window edge, keeping it below a 5.

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?

Front-loaded with the core action, then the required arg, then the record shape and routing. It is dense but every sentence carries information; the tail metadata ('Phase: observe; cost=low; idempotency=read-only ... Safety: read-only') slightly duplicates the annotations.

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?

With no output schema, the description usefully supplies the return record shape and error alternation, plus a failure fallback pointing at tool-schema. Only the boundary behavior of from/to/limit (e.g. what happens when the range exceeds limit) is left unexplained, so it is nearly complete rather than fully so.

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 baseline is 3, but the description adds semantics the schema does not: the range is seq-based, 1-indexed and inclusive, and from/to bound that range while limit caps output. This goes beyond restating field names.

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?

States a specific verb+resource+scope: 'Read a window of recorded tool calls from one session's JSONL trace', and immediately scopes it to a single session with a seq range. This distinguishes it from session-list (which produces the id) and session-replay (which consumes the output), so an agent can route without opening either schema.

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?

Gives concrete context: use it for auditing what was run and for feeding session-replay, and tells the caller where sessionId comes from ('from session-list'). It stops short of stating exclusions (e.g. when to prefer session-replay instead), so it is clear but not a full when/when-not/alternative matrix.

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