Extract bounded phrases locally or import reviewed evidence without network collection to keep keyword analysis offline and auditable.
Run bounded local phrase extraction or reviewed evidence import without network collection.
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | Yes | ||
| plugin | Yes | ||
| options | No | ||
| operation | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.22Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and openWorldHint=false, and the description usefully reinforces the closed-world constraint with 'bounded', 'local', and 'without network collection'. However, 'reviewed evidence import' implies ingesting external data into some store, which sits in tension with readOnlyHint and is left unexplained — the description does not clarify whether the import persists anything.
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?
It is a single compact sentence with no filler, which is good, but the compression has been taken too far — the key operational detail (which plugin/operation combinations exist) is absent rather than merely concise. Front-loading is fine; the problem is omission, not length.
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?
An output schema exists, so return values need not be described. For a three-required-parameter dispatcher with 0% schema documentation, though, the description leaves the agent unable to invoke the tool correctly, and no sibling tool provides a fallback path since no other keywordmoves_* tools are listed.
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% and there are four parameters, including three required ones (plugin, operation, inputs) plus an untyped options bag. The description supplies no valid values, no format hints, and no relationship between plugin and operation, so the agent has no way to construct a correct call from the definition alone.
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 names two concrete capabilities (phrase extraction and reviewed evidence import) but frames them through an opaque generic dispatcher, so the agent still cannot tell what 'plugin' or 'operation' values actually select. 'Run' plus a compound resource phrase gives partial differentiation, but the tool's real scope is only half revealed.
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 'without network collection' implicitly excludes remote/online workflows, which is the only usage signal present. There is no statement of when to pick phrase extraction versus evidence import, no prerequisites, and no mention of what 'bounded' or 'reviewed' constrain in practice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.