Search server files by substring to locate code, views, scripts, and template assets. Excludes manifests and core files for targeted results. Case-sensitive matching optional.
Substring search over the server files: unit code and its views, root scripts and .htaccess, css and js of every template set. Manifests, core and images are out of it.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | ||
| sensitive | No | Match the case. Off by default. |
Changes observed during successful MCP inspections.
v6.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full behavioral disclosure burden. It states the operation is a substring search but does not mention whether it is read-only, what the return format looks like, or any side effects. It only clarifies scope, not behavior beyond the obvious search semantics.
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 tightly worded sentences with zero fluff. The action and scope are front-loaded, and the exclusion list is given in a compact second sentence. Every word earns its place.
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 simple search tool with two parameters and no output schema, the description covers the inclusion/exclusion scope well but omits the return format and any note on read-only status. Given the tool's simplicity, it is minimally adequate but leaves the agent to infer typical search behavior.
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 coverage is 50% — only 'sensitive' has a description, while 'keyword' is undocumented. The description adds meaning by calling it a 'substring search', implying keyword is the search string, but it does not elaborate on format or constraints. It provides marginal value beyond the schema, partially compensating for the missing keyword documentation.
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 clearly states the verb (substring search), the resource (server files), and precisely enumerates what is included (unit code and views, root scripts, .htaccess, css/js of template sets) and excluded (manifests, core, images). This specificity distinguishes it from sibling file-loading tools without ambiguity.
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 description gives explicit scope boundaries, which implicitly tells the agent what this tool covers and what it does not, but it does not explicitly state when to prefer it over an alternative or mention any sibling tools. It lacks direct 'use this for X, not for Y' guidance, though the scope listing partially serves that purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.