Add Document

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

Annotations already declare readOnly=false, idempotent=false, destructive=false, openWorld=true. The description adds genuinely new behavioral context beyond those: it 'consumes the plan's document allowance' (cost/quota side effect) and warns that it does not read local files, setting a boundary on what the tool will not do.

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?

Two front-loaded sentences with zero waste: usage condition first, then side effects and the local-file boundary. Every clause earns its place.

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 2-param tool with no output schema and full annotation coverage, the description covers purpose, trigger, cost, and a key limitation. It leaves return behavior (e.g., document id) and duplicate-handling implicit, but those are minor against the annotated contract.

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 both 'content' and 'source' are already documented in the schema. The description only gestures at 'supplied text' for content and adds no format, length, or source-label semantics. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Specific verb+resource: 'persist supplied text' and 'Creates a searchable document' in the 'authenticated tenant's hosted Bee knowledge base'. An agent can distinguish this ingestion/write action from sibling reads like bee_documents_search without opening either 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?

'Use only when the user intends to persist supplied text' gives a clear triggering condition, and 'it does not read local files by itself' draws a useful when-not boundary. However, it never names the obvious alternative (bee_documents_search) to route retrieval-vs-ingestion intent explicitly.

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