prepare_host_run

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the useful note 'accepts no model credentials,' which clarifies it's not a model-invoking endpoint. However, it doesn't describe what the returned plan contains, what 'canonical' means, or any ordering prerequisites relative to other run lifecycle tools.

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 a single concise sentence with no wasted words. It front-loads the core action effectively. However, the terseness comes at the cost of under-specification—it's efficient but insufficient.

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?

This is a 7-parameter tool with no schema description coverage and no behavioral disclosure beyond annotations. While an output schema exists (which helps somewhat), the description doesn't explain inputs, prerequisites relative to the host-run lifecycle, or what distinguishes it from 10+ sibling run-management tools. For a tool with this complexity and sibling density, the description is materially under-specified.

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 description coverage is 0%, and the description mentions none of the 7 parameters. Two parameters are required (symbol, as_of_date) but the description doesn't say what these mean in the context of a 'host run' plan, nor how options like analysts, risk_rounds, debate_rounds, or output_language influence the returned plan. With zero coverage and zero parameter explanation, the agent must guess parameter semantics entirely from names.

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 says 'Return the canonical plan for the active host harness' which names a specific verb (return) and resource (canonical plan), but 'active host harness' is vague jargon that doesn't clarify what the plan actually contains or represents. Among 27 sibling tools (prepare_fixture, create_host_run, import_host_run, etc.), there's no clear differentiation about how this 'prepare' step differs from create/start/import/finalize runs.

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 no guidance on when to use this versus the many sibling tools dealing with runs (create_host_run, import_host_run, start_host_run, commit_host_stage) or other prepare-type tools (prepare_fixture). 'For the active host harness' implies a prerequisite state but doesn't state it explicitly or exclude alternatives.

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