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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds destruction granularity ('replace entirely' vs 'replace a section' vs 'add to end'), but that same text is duplicated in the operation enum in the schema, and it omits dry_run and the idempotency_key requirement for append.

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 tight sentences with the purpose front-loaded before the operation list; nothing is padded. It loses a point only because the operation recap partially duplicates the schema enum descriptions.

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 6-parameter multi-operation write tool with no output schema, the description covers all four modes and their effects on the document. It is slightly thin on dry_run behavior and the retry/idempotency contract, which are left entirely to the schema.

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 83%, so the schema already documents content, heading, document, operation and idempotency_key. The description adds no parameter-level detail beyond that and says nothing about dry_run, so the baseline 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 states a specific verb set and resource ('Read or update the AI memory document') and enumerates the four operations with their effects, so an agent knows exactly what the tool does. It cannot differentiate against a sibling because no sibling memory tool exists, keeping it just short of 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?

Operation semantics ('read (get current)', 'update (replace entirely)', 'patch (replace a ## section)', 'append') imply which mode fits which need, but there is no explicit when-to-use/when-not guidance, no guidance on choosing patch over update, and no mention of the dry_run preview path.

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