split_attentionSet attention weights for multiple running sessions at once. Use this to rebalance focus across active work, and use edit_session for completed sessions.
Set attention weights of the running sessions at once, e.g. {"abc": 0.7, "def": 0.3}. Applies to the whole session. For a finished session use edit_session.
| Name | Required | Description | Default |
|---|---|---|---|
| shares | Yes |
Changes observed during successful MCP inspections.
v0.4.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is carried by structured data. The description adds the scope of effect ('at once', 'Applies to the whole session'), which is real value, but it says nothing about permissions, conflicts, or how omitted sessions are handled.
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 plus an inline example; the core action is front-loaded and every element (set weights, whole-session scope, finished-session alternative) earns its place with no filler.
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 batch mutation with a nested-object parameter and 0% schema coverage, the description covers purpose, scope, and the sibling alternative, and annotations cover the safety profile (no output schema needed). The remaining gap is parameter meaning—keys, summation, and partial-update semantics—which leaves it adequate but under-specified.
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 0% on a required nested object, so the description bears compensating weight. The inline example {"abc": 0.7, "def": 0.3} does show the key→number shape, but the description never states that keys are session identifiers, whether weights must sum to 1, or how excluded sessions behave.
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 gives a specific verb and resource ('Set attention weights of the running sessions') plus a concrete data example, and it explicitly names a sibling case ('For a finished session use edit_session'). The concept 'attention weights' is domain jargon left unexplained, and it does not distinguish itself from other set_* tools, so it falls 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?
It states the operative condition ('running sessions') and gives an explicit alternative for the finished-session case ('use edit_session'). It does not cover the broader when/when-not against other state-setting siblings, so it is clear context without full routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.