create_host_run

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

All annotations are false (readOnlyHint, openWorldHint, idempotentHint, destructiveHint all false), so the description must convey the behavioral profile. The phrase 'durable' suggests persistence beyond a session, and 'credential-free' suggests no authentication requirement, both useful additions. However, it doesn't explain what a host run is, how decision-memory recall works, or what side effects creation entails. The description adds some context but lacks depth on lifecycle implications.

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 that gets to the point quickly. It's front-loaded with the primary action ('Create a durable credential-free host run'). While it's succinct, it may be under-specified rather than elegantly concise — the brevity sacrifices needed detail about parameters and use cases.

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?

Despite having an output schema (which reduces some burden for return values), the tool has 8 parameters with 0% schema coverage, no parameter descriptions, and a dense domain (host run creation with decision memory, analysts, risk and debate rounds). The description provides only a one-line summary that leaves the agent guessing about parameter semantics, lifecycle relationships with sibling tools, and behavioral implications of 'credential-free' and 'decision-memory recall'.

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%, so the description carries the full burden for explaining the 8 parameters, including 2 required ones (symbol, as_of_date). The description adds no parameter-level detail whatsoever — it doesn't allude to what 'symbol' specifically refers to, the format of as_of_date, what analysts or risk_rounds control, or what decision_memory_enabled does. This is a significant gap given zero schema coverage.

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 states 'Create a durable credential-free host run' which uses a specific verb (create) and identifies a resource (host run), distinguishing it from sibling tools like get_run or start_host_run. However, it relies on technical jargon ('durable', 'credential-free', 'decision-memory recall') without defining these concepts, and doesn't clarify the relationship to siblings like prepare_host_run, start_host_run, or import_host_run. The purpose is adequately clear but not thoroughly differentiated.

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 offers no guidance on when to use this tool versus alternatives such as prepare_host_run, start_host_run, or run_fixture. Given the abundance of host-run-related siblings, the agent cannot determine which creation path to choose. The mention of 'credential-free' implies a specific context, but no explicit when-to-use or when-not-to-use guidance is provided.

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