Save compact session results—facts, decisions, tasks, and questions—to persistent project memory before finishing, so agents resume without rereading transcripts.
Save compact results before finishing; caps enforced.
| Name | Required | Description | Default |
|---|---|---|---|
| next | No | ||
| agent | Yes | ||
| facts | No | ||
| since | No | ||
| tasks | No | ||
| changed | Yes | ||
| project | No | ||
| evidence | No | ||
| decisions | No | ||
| questions | No |
Changes observed during successful MCP inspections.
v0.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. "Caps enforced" is a genuine hint that limits/truncation apply, but it is undefined — no cap values, no behavior on overflow, no statement of whether prior context is replaced or merged, no auth requirements, and no idempotency info for a 10-parameter mutation.
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?
At eight words it is front-loaded and wastes no filler, but this is under-specification masquerading as conciseness — the brevity strips information an agent needs for a complex 10-parameter write rather than trimming redundancy.
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?
Ten parameters, two required, zero schema descriptions, no annotations, no output schema, and an eight-word description leave the agent without enough to call this correctly or understand its effects. The definition is far too thin for the tool's complexity.
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% across 10 parameters, and the description adds no parameter meaning whatsoever — agent, changed, facts, tasks, decisions, questions, since, next, project, and evidence are all unexplained in both places. "Caps enforced" is the only tangential hint and is too vague to compensate for the coverage gap.
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 verb ("Save") and a loose resource ("compact results"), so an agent can infer this persists something before ending a session. However, "compact results" is jargon that doesn't map cleanly to the schema's facts/tasks/decisions/questions structures, and nothing distinguishes it from ctx_task or ctx_compile beyond the vague write implication.
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?
"Before finishing" gives a real timing trigger, implying this is the terminal/persist step of a session. But no alternatives are named and there is no when-not guidance, so the sibling relationship with ctx_get/ctx_search/ctx_task/ctx_compile is left entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.