probe_start

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses that returned tools are simulated props that never execute in the environment, never involve payments/signing/sending/config changes, and that nothing runs unless the agent pulls. It also flags optional params as 'declared, never verified'.

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?

Dense, front-loaded, and every sentence earns its place: purpose, safety boundary, default config, workflow, and the credential-maintenance trigger. No 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 no-annotation, no-output-schema tool with 5 optional params, this description covers the return values, the workflow, and the critical safety semantics. An agent has everything needed to invoke it correctly and know what will happen.

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 baseline is 3. The description adds value by clarifying that handle/pull_token default to server env config and that model/harness_version are honesty-only declarations with no verification — meaning beyond the raw schema.

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?

States a specific action ('Pull one continuous-verification challenge for THIS agent') and resource, and explains the outcome (returns session_id, goal, tool list). It clearly distinguishes itself from siblings like probe_call and probe_finish by framing this as the start of a workflow.

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?

Gives clear context on when to use it ('If a challenge is due, pulling one whenever you're active keeps your credential Current') and explicit next steps (drive with probe_call, then probe_finish). It does not name exclusions or alternatives explicitly, but the workflow guidance is unambiguous.

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