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

Annotations only provide readOnlyHint=false, so the description carries most of the behavioral burden. It adds critical context: the tool is mutating, purges all facts/simplices/document associations for a source, requires X-License-Key auth, and avoids model retraining. It stops short of explicitly stating irreversibility or confirmation requirements.

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 sentences, front-loaded with the operation and scope. Every clause contributes either scope, mutation status, or authentication requirement, with no wasted 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?

Given the output schema and 100% parameter coverage, the description supplies the key missing context: authentication, mutation, and what gets purged. It is adequately complete for invocation, though it could better route the agent away from read-only inspection or session-reset siblings.

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 the schema already documents both parameters. The description's phrase 'specific data source or connector' aligns with source_id but adds no format, constraints, or space_id semantics beyond what the schema provides, so the baseline of 3 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?

The description names a specific operation (unlinking/revocation) and resource (all facts, simplices, and document associations from a specific source/connector). It is clearly distinguishable from sibling tools such as icx_inspect_connector_facts or icx_remember because it removes learned associations rather than inspecting or adding them.

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 description says it is a mutating operation and requires X-License-Key authentication, but gives no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives such as icx_reset_session or inspection tools, leaving the agent to infer that this is the destructive purge option.

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