quipu_set

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

Goes well beyond the destructiveHint/readOnlyHint annotations by spelling out that every current object on the predicate is retracted and the new one asserted in a single transaction, with no intermediate empty-predicate state, plus that a supplied graph field is refused. Slight gap: it does not say what is returned (transaction id, prior values) or whether the retraction is recoverable, which matters for a destructive 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 operation and scope, then atomicity, then the alternative. Dense and mostly earning its place, though the graph restriction is stated twice (description and schema) and the 'two supervisors' illustration, while useful, is the most expendable sentence.

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 destructive, 7-parameter, no-output-schema mutation this covers scope, atomicity, destruction, typing and routing to siblings. Minor omissions remain: no mention of return payload or how to recover the superseded value, and no guidance on actor/source/timestamp beyond the schema.

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 still adds real semantics, notably that predicate is single-valued and value must be typed as a literal or {"iri"} with bare strings refused on IRI-valued predicates. It also reinforces the graph-field refusal. The rest of the parameter meaning is already in the schema.

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?

States a specific verb (SET), the exact resource tuple (entity, predicate) and the scope (ROOT/default graph only), and explicitly contrasts itself with quipu_knot (additive assert) and quipu_update (named-graph writes). An agent can pick this tool over its 70+ siblings without opening a schema.

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?

Gives a concrete use case (re-parenting reports_to A -> B), names the exclusion (named graphs belong to quipu_update) and names the alternative for the additive case (quipu_knot). When-to-use, when-not-to-use and the substitute are all present.

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