add_hypothesis

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

No annotations are supplied, so the description carries the full behavioral burden. It never says that this creates and persists a new hypothesis, what happens with duplicate or overlapping statements, whether the write is reversible, or how confidence interacts with the record — all material for an unannotated mutation tool.

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?

Front-loaded with the core action and then terse, imperative clauses with no filler. The telegraphic fragments are slightly clipped but each carries field-level instruction, so almost nothing is wasted.

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?

With 7 parameters, no annotations, and no output schema, the description does enough to call the tool but not to call it well — the confidence scale, the identity of the case parameter, and the relationship to update_hypothesis remain 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 description coverage is 0%, and the description rescues the genuinely ambiguous fields: klass sources, supports/conflicts are claim ids, and would_falsify is a falsifying observation. It leaves case, statement, and especially confidence (a number with no stated range or scale) unexplained, so compensation is partial for a 7-parameter tool.

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 verb phrase 'Propose an explanation' plus the name add_hypothesis makes the resource concrete, and referring to klass via list_classes() anchors it to the domain model. It does not distinguish itself from add_claim or update_hypothesis, so an agent cannot fully rule out the siblings from the text alone.

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?

There is one genuine prerequisite — klass must come from list_classes() — which is helpful routing guidance. But there is no statement of when to create a hypothesis versus updating an existing one or adding a claim, so the when-to-use decision is only implied.

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