claim

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

No annotations are provided, so the description carries the full burden and does well: it discloses auto-naming, the settled-vs-open lifecycle, and that open claims are repeatedly resurfaced by `awake` until a verdict arrives. It does not state return value or whether late verdict attachment is possible, but the core behavioral model is conveyed.

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 purpose and the auto-naming rule are front-loaded, followed by the verdict branch and the open-question consequence. Three sentences with little waste; minor redundancy between the verdict sentence and the schema's own verdict description.

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 6-parameter tool with no output schema and no annotations, the description covers the primary workflow paths (settled claim, open claim, optional linking) well enough to call correctly. It stops short of describing what the created node looks like on return or the effect of `initiative`/`layer`, leaving minor gaps.

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 83%, so the schema already documents most parameters including the accepted verdict vocabulary and the `by` citation semantics. The description still adds meaning by framing `verdict`/`by` as the one-call settled path and `about` as a relationship link, tying the parameters to an outcome rather than just restating types.

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 specific verb+resource ("Record a hypothesis") and immediately adds the auto-naming behavior, so an agent knows exactly what this tool creates. It does not explicitly contrast itself with nearby siblings like `evidence`, `cite`, or `refute`, which would push this to a 5.

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 gives a clear conditional: pass `verdict` + `by` when you already know the outcome ("the usual case"), omit them for a genuinely open question. It also states the downstream consequence ("`awake` will keep surfacing it"). What's missing is routing against alternative tools such as `settle`, `refute`, or `inconclusive`, which likely overlap with the verdict path.

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