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

Although annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=true, the description adds the substantive behavioral facts: exactly what is destroyed (every learned passage), that website/social/profile sources are re-learned on the next refresh or profile save, and that human confirmation is required. This is context an agent cannot infer from the annotations.

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 destructive action, then prerequisites and caveats. Dense but no filler; the long parenthetical source list is functional rather than decorative, though the re-learning caveat sentence is slightly convoluted.

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, no-output-schema mutation, the description covers consequences, reversibility, confirmation, and the permanent-deletion path. The only gap is that workspaceId remains unexplained in both schema and description.

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 67%; `source` and `idempotencyKey` are both documented in the schema, and the description only restates that `source` must be exact and come from list_knowledge_sources. It adds no information about the undocumented `workspaceId` parameter, so the baseline 3 for moderate coverage applies.

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 ('Delete every passage Sparky learned from one source') with an enumerated list of what counts as a source (uploaded file, websites, social style, taught text). It is clearly distinguishable from siblings like forget_brand_fact or delete_style_examples, which act on single facts or style examples rather than a knowledge source.

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 states the prerequisite (pass the exact `source` from list_knowledge_sources), a workflow rule (confirm with the human first), and the follow-up alternative when the deletion must be permanent (also remove the site/page via update_brand_profile). When-to-use, when-to-escalate, and the sibling to call are all named.

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