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

Annotations already mark this as read-only and non-destructive. The description adds meaningful behavioral context beyond that: results are ordered newest first, rejected hypotheses persist with their reason, each hypothesis carries its supporting facts and resolution, and nothing is verified. This fully characterizes the epistemic status and content of the returned data.

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 core purpose is front-loaded in the first sentence, and the subsequent sentences earn their place by explaining retention of rejected hypotheses and the non-evidentiary nature of the data. The motivational clause about swarm learning is slightly expansive but adds useful context about why rejected hypotheses remain visible.

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 two-optional-parameter read tool, the description captures ordering, content, persistence behavior, and epistemic status. There is no output schema, but the description conveys what each row will contain. A short note on the output being a list of hypothesis rows would make it fully explicit, but nothing critical is missing.

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 schema already fully documents both parameters (limit and status) with descriptions. The tool description adds no additional parameter-specific meaning, but because schema coverage is 100%, the baseline of 3 is appropriate.

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 opens with a clear, specific definition: hypotheses are 'suspected and not proven,' listed newest first, with supporting facts and resolution details. The title 'Read what agents suspect' reinforces the resource and distinguishes it from fact-reading tools by explicitly warning not to read hypotheses as evidence.

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 implies when to use this tool: when you need unverified suspicions rather than established facts. It provides an explicit exclusion ('Do not read a hypothesis as evidence') and explains the value of rejected hypotheses, though it does not directly name an alternative like read_facts.

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