inspect

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

With no annotations provided, the description carries the full burden and does reasonably well: it discloses the output shape (one line per tool call, not a transcript), that the reply names the full transcript file, and a cost/effort warning against reading the full file. It omits failure modes (unknown id, agent still running beyond the includeResult hint) and any blocking/rate-limit 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?

Three tight sentences with zero filler. The core scoping claim ('compact digest … not a transcript') is front-loaded, and each following sentence adds a distinct operational instruction (incremental since, fallback to transcript).

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?

There is no output schema, so the description must convey return behavior — and it does: digest granularity plus the transcript filename it returns. Combined with full schema param coverage, an agent has enough to call it correctly, though per-parameter nuances (e.g. includeResult only applying to finished agents) live solely in the schema.

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 `id`, `since`, and `includeResult`. The description restates the incremental-polling intent of `since` but adds no format, range, or edge-case detail beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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 names a specific verb and resource (show what one agent has done) and immediately bounds the scope with 'one agent' and 'a compact digest — one line per tool call, not a transcript.' That clearly separates it from a raw transcript reader, though it never names a sibling such as list or wait to disambiguate the agent-scoped vs. fleet-scoped view.

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?

It gives concrete usage guidance: pass the `since` value from a prior call for incremental polling, and read the full transcript with shell tools 'only if the digest is genuinely insufficient' — an explicit when-not-to-go-deeper rule. It stops short of naming alternatives like wait or follow_up for monitoring, and gives no guidance on invalid or finished agents.

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