flowforge_manage_knowledge_bases

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

The annotation set already declares destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the 'delete' verb in the description is consistent rather than informative. The description does not disclose what deleting a knowledge base does to the documents inside it, nor that names are unique (409 on collision) or that 'update' can also change the description, though the latter two are covered in the schema. With annotations carrying the safety profile, a 3 reflects modest added context.

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?

One well-formed sentence with the action set front-loaded and the resource definition tucked into a parenthetical. No filler or repetition; the only slight inefficiency is that 'read'/'rename' do not match the enum labels 'get'/'update', costing a little clarity rather than length.

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 five-action, destructive CRUD tool the description leaves meaningful gaps: nothing about deletion consequences (cascading document loss), nothing about name uniqueness/conflicts, and no guidance on selecting among actions. The presence of an output schema removes any obligation to document return values, and the confirm-gate for delete is documented in the schema, which keeps this at minimum-viable rather than inadequate.

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?

Top-level schema coverage is reported at 0% for the single 'params' wrapper, so the description must compensate, and it does so only partially: it explains that a knowledge base is a document group referenced by knowledge_base_id, which is genuine meaning beyond the schema. However, it maps its verbs to 'get' and 'update' rather than the enum values 'get'/'update', and it narrows 'update' to 'rename' while the schema shows update also takes a description, which understates the action's scope.

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 concrete verbs (List, read, create, rename, delete) bound to a specific resource (knowledge bases) and even defines the resource as 'named groups of documents an assistant points at via knowledge_base_id', which separates it conceptually from flowforge_manage_documents and flowforge_list_documents. It never names a sibling outright, so an agent still has to infer the boundary versus flowforge_search_knowledge.

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?

Usage is only implied through the action verbs: an agent can guess 'list' for enumeration and 'delete' for removal, but there is no statement of when to choose this tool over flowforge_search_knowledge, flowforge_list_documents, or flowforge_manage_documents. No preconditions or exclusions are given at all.

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