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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses a key side effect: the strategy enters CANDIDATE state and is never directly TRUSTED, which is critical for an agent to understand the tool's impact. It does not cover other behaviors like persistence or required context, but it does surface the most important behavioral guarantee.

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 only three sentences, with the core purpose front-loaded and the critical trust-state caveat clearly highlighted. Every sentence adds essential meaning and there is no wasted text.

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 9-parameter tool with no annotations and zero schema coverage, the description leaves major gaps about how to construct a valid strategy object and when this tool fits in the wider experimentation workflow. The output schema exists, so return values may be partially covered, but operational guidance on parameters and prerequisites is largely absent.

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 provides no guidance on what the parameters mean, how they relate to a strategy, or how to populate fields like procedure, experience_ids, or applicability. The agent must infer semantics solely from parameter names and types, which is insufficient for a 9-parameter tool.

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 uses a specific verb and resource ('Propose a candidate strategy') and clearly distinguishes this from siblings like verify_strategy. Mentioning that it creates a CANDIDATE state rather than a TRUSTED one further sharpens its purpose.

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?

It explicitly states this tool never makes a strategy TRUSTED and that the strategy requires objective verification, which implies it should be used for candidate generation and not finalization. It does not name alternatives or explicit 'use when' conditions, but the sibling set and the state distinction provide clear context.

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