Search local AI-agent conversation history by exact phrase across sessions, canvases, and memories; returns verbatim snippets with source pointers.
Where these exact words were asked (Q), answered (A) or attached (M) across local sessions, canvases and the memories Claude Code and Codex keep for themselves. Exact, case-insensitive match; every hit is a verbatim snippet with a pointer.
| Name | Required | Description | Default |
|---|---|---|---|
| in | No | ||
| limit | No | ||
| phrase | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that matching is exact and case-insensitive (not semantic/fuzzy) and that results are verbatim snippets with pointers, but says nothing about result limits, permissions, or what happens on no-match.
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 dense sentences with little waste, but the lead phrase 'Where these exact words were asked' is grammatically awkward and front-loads a clause rather than the action or resource, forcing the reader to reconstruct the purpose.
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 3-param, one-required tool with no annotations and no output schema, the description covers matching semantics and return shape reasonably, but omits the meaning of 'limit' and any routing guidance relative to its siblings, leaving gaps an agent would need to guess at.
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. It does decode the 'in' enum values (asked/answered/attached) which is genuinely additive, but 'limit' is completely unexplained and 'phrase' is only obliquely referenced as 'these exact words'.
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 scopes the corpus (local sessions, canvases, Claude Code/Codex memories) and the operation (exact, case-insensitive matching), but never states a clear leading verb and never distinguishes itself from siblings like recall_turn or why_file. An agent gets the search domain but must infer that this is a literal full-text 'find' rather than a semantic lookup.
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?
There is no guidance on when to use this tool versus the sibling tools recall_turn, why_check, or why_file, and no stated prerequisites or exclusions. The Q/A/M breakdown hints at scope but is not framed as selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.