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

With only readOnlyHint=false and destructiveHint=false, the description adds meaningful behavioral context: hypotheses persist in the swarm's memory, are visible to readers, are never counted as facts, and later resolutions (even rejection) are treated as knowledge. This goes beyond the minimal annotation set without contradicting it.

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 moderately concise and front-loads the core action and purpose. The final sentence about rejected hypotheses being knowledge is slightly philosophical but does add lifecycle context, and the whole text remains short enough to scan quickly.

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 simple tool with only one required parameter, no output schema, and no nested objects, the description covers the essential invocation context: what to write, why supporting facts matter, and how the recorded hypothesis will be treated. It does not detail the target parameter, but the schema already handles that.

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%, so the baseline is 3. The description reinforces the importance of supporting_facts ('Say which facts it rests on') and adds rationale about hunches being costly, but it does not add significant new meaning beyond the schema's own parameter descriptions.

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 clear verb and resource ('Write down what you suspect') and emphasizes that a hypothesis is not a fact and must be testable, which distinguishes it from fact-recording tools. It does not explicitly name sibling tools, but the conceptual contrast is strong enough to identify the tool's 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?

The description gives clear context: use this when you have a suspicion you want others to test, and back it with supporting facts. It also warns against submitting unsupported hunches, which functions as a 'when not to' guideline, though it does not explicitly name alternative tools.

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