resume_run

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

With no annotations provided, the description carries the full burden — and it delivers. It discloses the local-state dependency (~/.verigent/state.json with mode 0600), the server error conditions (no_open_run, expired resume window), the success routing via next_action, and the side-effect-free relationship to continue_run. This is rich behavioral context beyond any structured field.

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 long (~130 words) but front-loaded with purpose and every sentence earns its place given the tool's complexity — state dependency, error codes, and sibling routing all need coverage. It loses one point for density; the flow could be tightened with clearer separation between success-path and failure-path guidance.

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 complex tool with zero annotations and no output schema, this is remarkably complete. It covers preconditions (saved state from start_verification), the only parameter's selection logic, post-success behavior (follow next_action), and all documented failure modes with the correct fallback tool. Nothing an agent needs to invoke it correctly is missing.

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 meaning beyond the schema by explaining when agent_id matters ('when this server has started more than one' saved run) and the selection fallback ('most recently saved one'). This is genuine added semantics, though the schema already captured the default behavior.

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 opening clause states a specific verb+resource+context: 'Resume a verification run after a cold session.' It distinguishes itself from siblings by explicitly contrasting with continue_run (which can be called directly) and start_verification (which should be called if nothing is saved). The endpoint is also provided.

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?

Exceptionally explicit. It says when to use the tool (cold session resume), when not to (continue_run already picks up the saved run_token, so resume_run can be skipped), and what to do on failure (call start_verification if nothing saved, no_open_run, or expired). It also names next_action routing (continue_run vs get_result).

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