Search shared project memory to retrieve relevant decisions, tasks, and facts without re-reading transcripts. Use a query and optional project or result limit to find prior context.
Search shared memory.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | ||
| q | Yes | ||
| project | No |
Changes observed during successful MCP inspections.
v0.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it says only 'Search shared memory.' It does not disclose read-only vs mutating behavior, whether the search is keyword/semantic/hybrid, result limits, permissions, or what a match looks like. This is a severe gap for a search tool with zero structured safety hints.
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 single sentence is short and front-loaded, but this is under-specification rather than conciseness. Nothing here would be cut for being redundant; instead, essential content is missing.
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?
A 3-param search tool with no annotations and no output schema demands a description that explains query semantics, scope, and result behavior. The description supplies none of that, so an agent cannot safely invoke it without inspecting sibling tools or guessing.
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 the description does not mention any of the three parameters (q, k, project). An agent cannot learn that q is the query string, k bounds result count, or project scopes the search. With the schema doing none of the work and the description doing none either, parameter semantics are effectively absent.
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 (Search) and a resource (shared memory), so the basic intent is legible. However, it is generic and does not differentiate this tool from siblings like ctx_get, ctx_compile, or ctx_task, leaving the agent to guess the boundary. That is the definition of a vague-but-not-tautological purpose.
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 ctx_get or any other sibling, no mention of prerequisites, and no exclusions. The description offers nothing beyond the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.