Memory: change facts

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description adds material context beyond them: the operation is 'audited', the return carries a fact id and status, and 'forgetting is a soft delete' — a semantic nuance an agent would otherwise have to infer from the schema. It is strong value-add without contradicting the destructive 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 short sentences, front-loaded with the mutation scope, then the read-first routing, then the return/soft-delete caveat. Every clause carries information and nothing is repeated from structured fields.

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?

There is no output schema, so the description carries the burden of describing returns — and it does ('Returns the stored fact id and status'). Combined with annotations covering the safety profile and the schema covering per-action parameters, an agent has everything needed to call this correctly.

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 100% and the action enum plus per-action required-parameter documentation is already exhaustive in the schema, so the baseline is 3. The description restates the write/soft-delete framing but adds no syntax or format detail the schema does not already carry.

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 specific verbs (create, update, soft-delete) and the precise resource (a durable key fact in NAVIG memory). It explicitly distinguishes itself from the sibling navig_memory by directing reads there, so an agent can separate the write tool from the read tool without opening a 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?

It states a concrete usage rule — 'Use navig_memory to read facts first' — which routes the agent correctly against the closest sibling. It lacks explicit when-not-to-use guidance or mention of alternative paths for each of the three actions, so it stops short of full routing coverage.

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