propose_experiment

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

No annotations are provided, so the description carries the full burden. It hints at a permission-seeking behavior but does not disclose what happens after a proposal (e.g., state changes, side effects, approval workflow). There is no mention of mutability, destructive potential, or system impacts. This lack of detail limits an agent's ability to anticipate consequences.

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 extremely concise (one sentence) and front-loads the key action. However, it may be overly terse for a tool with 5 parameters and no annotations. It avoids verbosity but sacrifices some informative value. Still, it is well-structured for brevity.

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?

Given the tool's complexity (5 parameters) and lack of annotations or output schema, the one-line description leaves significant gaps. It does not explain the lifecycle of an experiment proposal, what happens after submission, or how it relates to sibling tools like 'complete_experiment' or 'get_pending_experiments'. The description is insufficient for full contextual understanding.

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%, with all 5 parameters having clear descriptions in the schema (e.g., 'What I want to try', 'Why it's interesting'). The tool description adds no additional meaning beyond the schema. Per guidelines, baseline is 3 when coverage is high, and no extra value is provided.

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 clearly states the tool's purpose: 'Propose an experiment I want to try (asking permission to explore)'. It uses a specific verb ('Propose') and resource ('experiment'), and distinguishes well from siblings like 'complete_experiment' and 'record_learning'. The added parenthetical clarifies the intent of seeking permission.

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?

No explicit guidance on when to use this tool versus alternatives. The context of 'asking permission to explore' implies it is for initial proposals, but there is no mention of when not to use it or which sibling to choose instead. The usage is implied but not clearly delineated.

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