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

The description asserts '(READ-ONLY: mutations refused)', but the annotations declare readOnlyHint=false, i.e. this tool performs writes. That is a direct contradiction about whether the call will mutate state at all, which is the single most important behavioral fact for the agent. The otherwise-useful details (hash/timestamp/reason revision entry, supersede-vs-consolidate semantics) cannot offset the conflict.

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 dense sentence that front-loads the action and mechanism, followed by a short parenthetical. Nothing is padded, though the parenthetical is the contradictory element and would have been better spent on a non-conflicting operational note.

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, and the description does explain what side effects are created (superseding record plus revision entry with hashes and timestamp), which is the right content for a mutation tool. However, the read-only claim leaves the agent unable to tell whether the call will succeed or be refused, so the definition is not fully sufficient to act on.

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%, so baseline is 3; the description still adds real meaning by framing `content` and `superseded_by_id` as two different modes (writing a new superseding record vs consolidating into an existing target) and by tying `reason` to the durable revision entry. This is genuine value beyond the per-field schema text.

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?

States a specific verb (update) and resource (memory) plus the mechanism used: writing a superseding record or consolidating, plus a durable revision entry. That mechanism distinguishes it from memory.create and memory.revisions without needing to name them, though no sibling is explicitly called out.

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?

Usage is only implied by 'Update an existing memory' and the required `id`. There is no statement about when to choose this over memory.create, memory.pin, or memory.aggregate, and no prerequisites or exclusions are given.

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