quipu_retract

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real behavioral detail on top: the graph field is actively refused, named-graph facts are left intact, and entity+predicate+value collapses to exactly one triple. It does not discuss irreversibility, what provenance/allow_orphan do to the removal, or what is returned, which keeps it from a 5.

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?

Three tight sentences, front-loaded with scope, then the refusal constraint, then the precision use case. No filler and no restatement of the tool name; every clause carries actionable information.

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 an 8-parameter destructive mutation with no output schema, the description covers scope, the refused parameter, and narrowing semantics, which is most of what an agent needs. Gaps remain around irreversibility and the effect of allow_orphan/source/timestamp on the retraction, though the schema covers those fields individually.

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 100%, so the baseline is 3; every parameter including graph and value is already documented in the schema. The description's only semantic addition is the combinatorial rule that entity+predicate+value pins a single (e,a,v) statement, which the value field description largely repeats.

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?

Names a specific verb (retract) and resource (ROOT/default-graph facts for an entity) and immediately bounds scope: whole entity, or narrowed by predicate and/or value. It also distinguishes itself from episode-level retraction and from graph-scoped updates, so an agent can identify it among siblings like quipu_retract_episode and quipu_update without opening schemas.

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?

Provides explicit when-to-use ('use this to remove a stray edge instead of retracting a whole episode and rebuilding it') and a hard when-not ('Supplying a graph field is refused; named-graph facts are untouched'). The alternative path for named graphs is identified, leaving little to inference.

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