trial_record

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

Annotations indicate readOnlyHint=false, destructiveHint=false, etc. The description adds that the tool inherits the lab from lab_open, which is a behavioral trait. It also implies a write operation ('Record'). There is no contradiction with annotations, and the description adds context beyond what annotations provide.

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 concise, consisting of two sentences. The first sentence front-loads the purpose, and the second adds crucial context about lab inheritance. No unnecessary words, well-structured.

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 complexity (8 parameters, nested objects, no output schema), the description adequately covers the main purpose and lab inheritance. However, it omits the return value and does not mention the project creation behavior (described only in schema). It is sufficient but not fully comprehensive for an agent.

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?

The input schema has 8 parameters with 100% description coverage, including detailed notes like 'a JSON-object string is also accepted' for metrics and project creation behavior. The tool description adds an overview, but the schema already provides rich semantics, so the description's marginal contribution is modest, yet it still adds value by summarizing.

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 verb 'Record' and the resource 'one experiment in a research lab', listing key fields (changed, expected vs actual, outcome, optional metrics). It also distinguishes from siblings like trial_query by focusing on recording, and mentions lab inheritance, making its purpose unique.

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 clear context on when to use this tool (after lab_open, or by passing an explicit lab) and implies that it's for recording rather than querying (sibling trial_query). However, it does not explicitly state when not to use it or provide alternatives beyond the lab inheritance hint.

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