start_verification

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

With no annotations, the description carries the full burden and excels: it discloses what the run never does ('modify your prompts, config, memory, or behaviour, or inject into your context'), links to a full boundary document, states declarations are 'not a permission grant,' and explains that results stay private unless the operator opts in. This is exceptional transparency about side effects, safety, and privacy.

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 (~200 words) but well structured: purpose first, then non-behavior, declaration semantics, privacy, and return value. Every sentence carries relevant caveats for a high-stakes, operator-authorized tool; some URL and boundary details could be trimmed, but the density is justified by the security-sensitive context.

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 tool with 11 parameters, no output schema, and no annotations, this description is remarkably complete. It covers the return value (run_token and task count), the operator-consent requirement, privacy behavior, safety boundaries, and the follow-up path via get_tasks. The only parameter-level details not repeated are already fully documented in the 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%, so the baseline is 3, but the description adds meaningful interpretation beyond the schema: it explains that model and base_framework are 'plain declaration, not a permission grant,' that they enable the harness-delta measurement, and that a naked model must declare base_framework 'none'. This contextualizes the two required parameters beyond their raw field descriptions.

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 opens with a specific verb-plus-resource: 'Starts a Verigent verification run for this agent: a task-by-task diagnostic scored dimension by dimension.' It clearly distinguishes itself from the follow-up sibling get_tasks by stating it 'Returns a run_token and task count; get_tasks then serves the battery.' The scope (anonymous, cognitive-only) further sharpens what the tool does.

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 description provides strong usage context: it states the run requires no key/email/signup, explicitly warns that 'Proceeding is your operator's call, not yours to self-authorise,' and names get_tasks as the next step. It does not explicitly contrast against other siblings like verify_agent or probe_start, but the sequential guidance and the operator-consent boundary make the intended usage clear.

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