session_close

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

With no annotations, the description fully carries the behavioral burden. It discloses a wide range of side effects and the refusal logic, plus the guarantee that accepted closes still record debt. This exceeds typical transparency requirements and gives an agent a precise model of what happens when the tool is invoked.

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 a single paragraph with a list of actions, front-loaded with the main purpose. Every sentence adds unique information (side effects, refusal condition, debt behavior). It is a bit long but not bloated; the structure is clear and scannable.

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 the tool's effects and refusal condition thoroughly but omits explicit guidance on several optional parameters and does not describe the return value (no output schema exists). For a complex 6-parameter tool, an agent would still need to infer the purpose of open_hooks, next_intention, and character_stories_awarded, making completeness only partial.

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% for 6 parameters, so the description must compensate. It explicitly explains accept_uncommitted and hints at public_summary (via 'writes a dated summary') and session_title (implied by name), but leaves open_hooks, next_intention, and character_stories_awarded unexplained. This is a significant gap for a tool with many parameters, and the parameter semantics are not adequately resolved.

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 main action 'Close the session' and enumerates all the specific side effects (writes summary, awards Stories, clears conditions, re-rolls, creates backup, opens next log). It differentiates from related siblings like scene_commit by explicitly referencing the refusal and the need to call scene_commit first.

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?

It provides explicit usage context: when to close a session, and a clear condition for refusal (unratified outcomes) with an escape hatch (accept_uncommitted=true). It also names the alternative (scene_commit) and the consequence of using the flag (debt is never silently dropped). This leaves little to inference.

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