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

Annotations already declare destructiveHint=true and idempotentHint=false, so safety is covered. The description adds genuine behavioral context beyond them: the consequence ('no longer reaches vacancy analysis or the agent') and the precise semantics of the 'not_found' outcome including the ownership-scoped case. It does not contradict any annotation.

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?

Three tightly written sentences, front-loaded with the action and identifier, then the effect, then the error case. No filler and every sentence carries new information.

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 single-parameter destructive tool with an output schema present, the description covers identifier source, deletion effect, and the not_found cases. Nothing critical is missing for correct invocation, though it could note whether the deletion is recoverable.

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?

Only one parameter and the description supplies its provenance ('as returned by get_career_memory'), which is the operationally important detail for producing a valid value. This largely compensates for the reported 0% schema description coverage, though it adds little else about id format.

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 ('forget') plus the exact resource ('a single career fact by its id') and it names the sibling that produces the id (get_career_memory). An agent can distinguish this from add_career_fact / upsert_career_memory without opening any 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?

The description tells you the fact is identified by an id from get_career_memory, which implies the get-then-forget workflow, but it never states when to prefer this over add_career_fact or upsert_career_memory, nor any preconditions beyond id provenance. Usage is implied rather than routed.

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