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

Beyond the annotations (readOnlyHint=false, non-destructive, non-open-world), the description adds substantial behavioral context: the run is billed as a test, trace=true returns ordered per-node steps with statuses, durations, written fields, tools called, a closed error_kind, trace_summary buckets, and a 'paused' flag at approval nodes. This is exactly the extra context annotations cannot carry.

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 core purpose and billing note are front-loaded, followed by the trace detail. It is a single dense block, but given the conditional trace semantics almost every clause carries information; minor tightening would help.

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 cover returns. It thoroughly documents the trace output and the non-workflow empty-trace/trace_note case, but does not describe the primary runtime reply payload, leaving a small gap for a tool whose main output is that reply.

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%, so the baseline is 3. The description goes further by explaining what trace=true actually returns and that it does not change the run or its billing, adding real meaning to the parameter beyond the schema's one-line 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?

The description gives a precise verb and resource ('Send a test message to a draft and get the real runtime's reply') and clearly frames the tool as a draft-testing probe. It only implicitly distinguishes itself from the sibling probe_deployment via the word 'draft'; it never names the alternative, so differentiation is inferred rather than stated.

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?

Usage is implied ('test a draft', 'billed as a test run') but there is no explicit when-to-use/when-not guidance and no reference to the sibling probe_deployment for deployed agents. An agent can infer the context but gets no routing or exclusion rules.

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