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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds valuable context beyond annotations: 'delete' removes a source and its vectors for good, and 'reprocess' re-chunks and re-embeds, and clarifies that reprocess is appropriate for error/stale sources. It does not, however, state that reprocess is not idempotent or discuss side effects like vector replacement beyond what the annotations provide.

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 a one-sentence summary, then action-specific guidance and source_id discovery. Every sentence earns its place, including the Args section which repeats necessary constraints efficiently.

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?

Complete enough for an agent to invoke: it knows what each action does, when to choose each, and how to obtain source_id. The only omissions are the user_intent parameter and any note that reprocess is not idempotent, but these are not critical for correct invocation given the annotations and 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 33%, so the description must compensate. It explains action's two enum values and their meanings, and describes source_id as the target (required) and how to find it. The user_intent parameter is not mentioned, but it is an analytics hint with its own schema description, so the gap is minor.

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 (delete or reprocess) and resource (a knowledge source), and names distinct actions with their purposes. An agent can distinguish this from get_knowledge and add_knowledge without opening sibling 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?

Explicitly explains when to use each action: 'delete' to remove, 'reprocess' as the fix for a source stuck in 'error' or stale after the page changed. It even points to get_knowledge as the way to find source_id, giving both when and where to use this tool versus an alternative.

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