mcp_engram_session_start

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

With no annotations, the description carries the full burden. It discloses the exact contents of the wake bundle (primary_goal, suggested_actions, trace_chain head, slim ego_snapshot, presentation_stratum previews, trust_residual), notes a verification step (local CRS verify), and instructs the agent on sequencing. This is substantive behavioral disclosure, though it omits details about idempotency or error handling.

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 dense but front-loaded with the mandatory nature. It packs a lot of operational detail into four sentences, and every sentence serves a purpose. However, heavy use of acronyms and domain-specific terms (CRS, presentation_stratum, trace_chain) may reduce readability.

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 session-start tool with no output schema, the description lists the bundle contents which serves as the expected output, and references documentation for deeper details. It covers the agent's immediate needs: what to expect, what to do, and what to avoid. It could mention the return value explicitly, but the bundle list suffices.

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?

All three parameters have schema descriptions, so the baseline for parameter semantics is 3. The description adds marginal context by linking 'primary_goal' to the intent parameter and confirming the default bundle, but it does not elaborate on include_spatial or spatial_max_files beyond the schema.

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 identifies this as the 'MANDATORY first MCP call every session,' which clearly establishes its role as session initialization. It distinguishes itself from siblings by describing the default slim wake bundle and pointing to mcp_engram_get_continuation_bundle for the full harness. However, it does not explicitly state 'this tool starts a session' as a direct verb-object phrase, relying on the mandatory-first-call framing.

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?

Provides explicit when-to-use ('MANDATORY first MCP call every session'), what to do after ('Execute suggested_actions BEFORE edits; ack with mcp_engram_ack_wake_queue'), and what not to do ('do NOT call watch_workspace at wake'). It also names the alternative for full harness, making usage context crystal clear.

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