Job Control

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

The description is consistent with annotations: 'observe or cancel' aligns with readOnlyHint=false (cancel is a mutation) and does not contradict destructiveHint=false. However, it adds little behavioral context beyond the annotations themselves. The schema's 'cancel drops your interest; shared work may continue' is valuable context but lives in the schema, not the description. With openWorldHint=true signaling potential external effects, the description could have disclosed more about side effects but doesn't.

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?

A single front-loaded sentence with zero filler words. The core action (observe/cancel) leads and the resource scope (explicitly submitted long-running operation) follows. Efficient, though so terse it borders on under-specification rather than disciplined conciseness.

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?

The output schema exists so return values need not be described, and annotations carry the safety profile. But for a 5-parameter tool with three distinct actions (status/wait/cancel), the description omits any guidance on which action to select and when. The presence of wait_seconds and interest_token suggests nontrivial interaction patterns that are undocumented in the description.

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?

At 60% schema coverage, two parameters (max_bytes, interest_token) lack schema descriptions and the description compensates for none of them. The description contains zero parameter information. An agent cannot infer what max_bytes or interest_token mean from either the schema or the description — a meaningful gap the description fails to bridge.

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 'Observe or cancel an explicitly submitted long-running operation' uses a specific verb pair and a precise resource type. It cleanly distinguishes itself from all eight siblings (service_status, library_overview, search_evidence, etc.), none of which deal with job lifecycle management — an agent can select this tool unambiguously.

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 'explicitly submitted' implies this tool is for jobs that were returned as pending, and the schema reinforces this with job_id described as 'From a pending result.' However, the description itself gives no explicit when-to-use guidance, no exclusions, and no named alternatives — the usage context is only implied, not stated.

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