mnemosyne_update_position

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is a mutation ('Update') and, notably, that this is 'persisted as a DECISION chronicle in the vault' — which hints at audit/immutability semantics beyond a simple field update. It does not state whether the write is append-only, idempotent, or requires certain permissions, but 'DECISION chronicle' adds meaningful behavioral context. A 4 is appropriate because the persistence trait is genuinely useful, but the description stops short of explaining side effects on prior positions.

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 with clear front-loading of the verb, resource, and specific call timing. The second sentence's chronicle detail adds useful behavioral context without bloating. Every clause earns its place.

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 simple three-parameter update with a full schema, the description adequately covers purpose, timing, and content. No output schema means return-value behavior is undocumented, but for an update tool this is less critical. The main missing context is what happens to an existing position (replaced, appended to a history, or stored as a new chronicle entry) — but the 'DECISION chronicle' phrasing partially covers this, so the overall package is solid but not complete.

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 the schema already documents all three parameters. The description contributes the grouping 'phase, current state, next steps,' which maps loosely to the 'phase' and 'position' parameters and clarifies the intended content. However, it doesn't add required-format guidance, examples, or relationship semantics beyond what the schema already says. Baseline 3 is correct when the schema carries full documentation.

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 ('Update'), a resource ('current position of a Resonance'), and the timing ('at the end of a session to record where you left off'). It also clearly distinguishes this from the sibling mnemosyne_get_position, which retrieves position rather than updating it. The only slight gap is that 'Resonance' itself is a domain term that isn't defined here, but the tool name and resource phrasing make the purpose clear.

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 gives explicit context for when to call the tool: 'Call this at the end of a session to record where you left off — phase, current state, next steps.' It does not explicitly list alternatives or when not to use it, but the sibling contrast with get_position is implicitly clear because this tool writes and get_position reads. An explicit exclusion statement would improve the score.

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