Persist include, exclude, or maybe screening decisions with reasons and confidence, attaching a reviewable decision ledger to a search ID for later export.
Persist include/exclude/maybe decisions and reasons from abstract-screening subagents. The decision ledger is attached to the search_id and can be exported or reviewed later.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| searchId | Yes | ||
| decisions | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden. It does disclose the useful post-condition that the ledger is attached to search_id and can later be exported or reviewed, but it is silent on the most important behavior for a persistence tool: whether repeated calls append, overwrite, or merge prior decisions, and whether it creates or updates the ledger. Permissions and error behavior are also unaddressed.
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?
Two sentences with no waste, front-loaded with the action, and the second sentence adds genuine lifecycle context rather than restating the first.
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?
This is a mutation tool with no annotations, no output schema, and a nested decisions array of five fields at 0% schema coverage. The description never says what a successful call returns (confirmation, counts, ledger id) or how the write behaves on repeat calls, which leaves meaningful gaps for an agent invoking it.
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%, so the description must compensate, and it only partially does: it names the verdict values (include/exclude/maybe), the presence of reasons, and the search_id linkage. It adds nothing about 'notes', the nested 'tags' and 'confidence' fields, or the schema's 1-100 item constraint on decisions.
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 states a specific verb ('Persist') and resource ('include/exclude/maybe decisions and reasons'), and ties the write to a search_id. No sibling tool saves screening verdicts, so an agent can immediately distinguish this from the search/download siblings without inspecting the schema.
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 phrase 'from abstract-screening subagents' implies the workflow position (after screening, before export/review), but there is no explicit when-to-use or when-not-to-use statement, and no alternative is named because none exists. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.