inspect

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

With no annotations, the description carries full behavioral burden. It explicitly discloses that logs/diffs stay on disk, that inspect reads slices rather than whole artifacts, and that `diagnose` returns a sanitized, size-bounded report with redacted secrets/emails/blobs and a stable `code` + `hints`. These are genuinely useful, non-obvious behavioral details.

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 compact, front-loaded with the core purpose, and uses a short list plus one focused bullet for the special `diagnose` behavior. Every sentence earns its place without redundant filler.

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?

For a read tool with no output schema and no annotations, the description covers purpose, allowed `what` values, disk behavior, and the important sanitization guarantee for `diagnose`. It could elaborate on the return shape of the other `what` variants and on offset/limit semantics, but the information provided is sufficient for basic correct invocation.

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?

The schema provides zero parameter descriptions and no enums, so the description's explicit `what: status | summary | diff | verify | log | raw | usage | diagnose` list adds real selection value. It does not explain `task_id`, `limit`, or `offset` in detail, but 'read slices here' and the default values make their roles inferable.

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 starts with a direct verb and resource: 'Read task details on demand,' and then enumerates the concrete read slices via the `what` list. This clearly distinguishes `inspect` from the process-oriented sibling tools (`run`, `wait`, `cancel`, `agents`).

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 phrase 'on demand' signals that inspect is the async/read-side counterpart to running or waiting, and the sibling names make the operational contrast obvious. It does not explicitly name alternatives or exclusion conditions, but the usage context is clear enough for an agent to route correctly.

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