end_session

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

With no annotations, the description carries the burden well: it discloses that multiple rows are written across two tables, that each entry becomes a typed record with a default importance (constraints=9, warnings/relational_delta=8, decisions/open_loops/next_session_focus=7, preferences=6), and that session_id triggers a warning about unreviewed PreCompact captures. It does not discuss idempotency, duplicate handling on repeat calls, or error behavior on partial writes, which keeps it from a 5.

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?

Front-loaded with the purpose, then behavior, then workflow — a sensible ordering with no filler sentences. It is on the long side for a description, and the type/importance enumeration partly duplicates schema descriptions, but each sentence still carries information an agent needs.

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 12-parameter mutation tool with a nested object, no annotations, and no output schema, the description covers write targets, linkage, retrieval paths, and the one response caveat (unreviewed capture warning). What it omits is the actual response shape and failure/duplicate semantics, which matters somewhat since no output schema exists.

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 coverage is 100%, so the schema already documents all 12 parameters including the nested provenance object. The description mostly restates that shape (checkpoint required, the rest optional) and adds only marginal meaning beyond it, such as the fact that checkpoint is what boot_report loads next session. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb and resource ('Capture a structured session handoff') and then enumerates exactly what gets written: one required checkpoint plus optional typed records and a session row. The typed-column / session_id linkage detail separates it cleanly from store_memory, which writes individual memories.

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?

Gives an explicit workflow directive — 'call end_session at the end of every substantive session' — which is clear positive guidance. It also names the downstream consumers (boot_report, search_memory, list_memories). It never says when NOT to use it or explicitly contrasts with store_memory for single-record writes, so the sibling routing is implied rather than stated.

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