aiworkhub_manager_session_write

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

With no annotations, the description carries the full burden and does well: it discloses that amend rebuilds FTS and rewrites the context-graph mirror, that redact deletes the document, its FTS row and its graph mirror, and that the audit record preserves only the fact of redaction, never the content. Remaining gaps are the semantics of the required idempotency_key (retry behavior) and any authorization or failure conditions.

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 two-mode structure is front-loaded and the action names are formatted code-style so they scan quickly against the enum. It is dense but nearly every clause conveys a distinct behavior; the only mild redundancy is restating that both edit actions require document_id after already listing them as a group.

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 mutation tool with an output schema, the description covers the destructive/rewrite consequences, the append-vs-edit branch, and the audit guarantees, which is what an agent needs before committing a write. Return values are handled by the output schema, so the only omissions (idempotency and provenance semantics) are peripheral to correct invocation.

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%, so the description must compensate, and it explains action, document_id (required for amend/redact, implicitly null for appends) and what happens to content under amend. It says nothing about three required parameters — topic, provenance and idempotency_key — leaving their meaning entirely to bare titles.

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 opening line gives a specific verb and resource ('append one audited canonical Session Manager event, or edit one existing event') and splits the tool into two clearly named sub-modes. It does not name a sibling to route against (e.g. aiworkhub_manager_session_current_state for reads, aiworkhub_manager_context_graph_event_write for graph events), so sibling differentiation is only implicit via the 'Session Manager' resource label.

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 append/edit split is made actionable by enumerating which actions belong to each group (start, event, checkpoint, state, handoff, close vs amend, redact) and stating that the edit actions require document_id. It stops short of when-not-to-use guidance — nothing tells the agent when to prefer a related write tool or what to do if the topic does not yet exist.

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