unlearn

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

Annotations already declare destructiveHint and idempotentHint, which lower the burden. The description adds an important fact beyond those annotations: using docid removes an entire document and its member sections, which is a cascading destructive effect an agent should know. It does not discuss reversal/auth/returns, but the main risk is disclosed.

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 sentence with zero waste, the principal action ('Remove') is front-loaded, and all follow-up information is packed in a single useful branching structure. The parenthetical about member sections is essential and does not bloat the text.

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?

Combined with the rich schema (including sectionType) and annotations, the description is enough for an agent to invoke the tool correctly for the main use cases. A little more context about sectionType default behavior or the return value could improve it, but for a destructive, idempotent deletion tool structured information covers most of the gaps.

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?

The schema already provides a description for every parameter, including the sectionType partition choices, so the description is not required to carry the parameter load. However, the description only restates what the schema says and introduces a slight terminology mismatch by saying 'docid' while the schema calls it a 'document kbid', which prevented extra value.

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 clearly names a specific verb and resource: a section can become a document can be removed, with the second mode explicitly editing all member sections. This makes the tool's purpose unmistakable in the broad sense. It does not explicitly route an agent away from the sibling skill-unlan and agent-unlan tools, so it does not fully earn a 5.

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?

The 'or an entire document by docient' wording implies when to use the doc mode instead of a single-section deletion. There is no explicit comment about when to use this tool over the skill- or agent-scoped siblings, and the sectionType parameter's role is not reflected in the description. Guidance is therefore decent but implicit.

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