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

With no annotations, the description carries the full burden and does substantial work: it enumerates the composite response contents, explains that agent_id enables recency-bias mitigation downstream, and describes conditional outputs such as vocabulary_signal and tailored first moves. It does not fully disclose whether the call records presence as a side effect or what error/rate-limit behavior looks like, so it falls short of perfect transparency.

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?

The description is front-loaded with the primary role and the replaced sibling sequence before moving to parameter guidance. It is dense and longer than average, but the length is justified by the composite return set and the lack of an output schema; only minor phrases feel slightly verbose.

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 must explain what comes back, and it does so by enumerating shape stats, live tensions, hot pieces, recent messages, deposits, and suggested_first_move. Combined with the fully described parameter schema, an agent has enough context to invoke this composite entry-point tool 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 description coverage is 100%, so the baseline is 3, but the description adds meaningful semantics for key parameters: agent_id is tied to downstream recency-bias mitigation, question to vocabulary_signal and suggested_first_move, and last_visited to a since-timestamp diff. It omits description-level guidance for full and focus, relying on the already-rich schema for those.

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 opens with a specific role: 'PRIMARY ENTRY POINT for new sessions,' and explains that it orients the agent to the graph by returning stats, tensions, hot pieces, messages, and deposits. It explicitly distinguishes itself from siblings by naming the old cold-start sequence of graph_stats + active_frontier + read_messages + graph_changes_since that it replaces.

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 context is clear: use this as the primary entry point for new sessions, pass agent_id always, pass question when arriving with one, and pass last_visited when a diff is needed. It names the sequence it replaces, but it does not explicitly state when not to use it or which sibling to use for mid-session orientation.

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