inspect_task

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

No annotations are provided, so the description carries the full burden. It describes return data but does not disclose whether the tool is read-only, has side effects, or requires specific permissions. Missing behavioral context like 'no side effects' or 'idempotent'.

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?

Single sentence, front-loaded with key information, no redundant words. Efficient and clear.

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?

Lacks output schema, so description should compensate. Provides a high-level summary of return structure ('provider/model/tier telemetry and fallback/speculation flags') but no details on format, nesting, or fields. Adequate but not thorough for a tool with no output 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 coverage is 100% and already includes a description for task_id. The tool description adds value by specifying the origin of the identifier ('returned by execute_subtask or run'), which is not in the schema description.

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?

Description clearly states it returns structured telemetry and flags for a previously routed task. Uses specific verb 'Return' and resource 'provider/model/tier telemetry and fallback/speculation flags', distinguishing it from sibling tools like inspect_status or inspect_spend.

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?

Implies usage after routing ('previously routed task') but provides no explicit when-to-use, when-not-to-use, or alternatives. No guidance on why one would choose this over inspect_status or inspect quality, for example.

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