mem_session_end

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the upserve behavior ('uses topic-upsert — one recap per scope is kept and updated in-place'), mentions that revision_count increments, and describes how get_briefing surfaces the latest recap. This goes beyond a simple write operation and gives the agent a clear mental model of side effects.

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 well-organized with clear sections (HOW IT WORKS, PARAMETERS, RETURNS) and front-loads the core purpose. It is somewhat long, but each section earns its place. The parameter list duplicates some schema information, but the added context (e.g., files_touched as staleness anchor) justifies the length. Minor redundancy prevents a 5.

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?

The description covers usage, behavior, and the return shape, which is helpful given the absence of an output schema. However, it omits the 'module' parameter and fails to clarify the scope=module requirement, creating ambiguity about when that parameter is needed. This gap makes the description incomplete for a tool with 7 parameters and conditional requirements.

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?

Although the schema coverage is 100%, the description's parameter section is misleading and incomplete. It lists scope as 'personal (default) | team' but omits the 'module' option present in the schema enum. It also drops the 'module' parameter entirely, which is required when scope=module. This introduces a conflict with the input schema and fails to add full semantic value.

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 clearly states the tool's purpose: 'Save an end-of-session recap so the NEXT session starts with fresh context.' It uses a specific action (save) on a specific resource (end-of-session recap) and explains the benefit. It also distinguishes itself from the autopilot auto-save and references get_briefing, setting it apart from sibling memory tools.

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 explicitly says 'CALL THIS before closing any significant working session' and contrasts manual use with the autopilot minimal automatic recap. This provides clear usage context. However, it does not explicitly name alternatives or exclusionary conditions (e.g., when not to use it), so it falls slightly short of a 5.

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