Skip to main content
Glama

Search Strings

search_strings
Idempotent

Search provider-defined string objects with literal or regex matching to find text in reverse-engineered artifacts. Results are deterministic over defined literals, not all bytes.

Instructions

Search every provider-defined string object using literal matching by default or regex when requested. Results are deterministic and complete over those defined objects, not every text sequence in artifact bytes. Ghidra may omit packed or undefined literals, including Rust strings; an empty result does not prove text is absent. If an address is known, read_bytes and xrefs inspect its bytes and references. Hopper retains typed byte decoding, native display, and explicit decoding unknowns. Adjacent long-literal fragments match independently. Hopper regex mode uses ECMAScript Unicode syntax in a cancellable worker; a matching deadline leaves its API usable.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mode": "literal",
      "pattern": "authorization failed",
      "case_sensitive": false
    },
    "name": "search_strings"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoOperation mode that selects the requested behavior.
patternYesThe literal text or regex pattern to search for
documentNoThe document name
case_sensitiveNoWhether to match case

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, and the description adds genuinely useful behavioral context beyond that: the result set is deterministic and complete only over defined string objects, Ghidra may omit packed or undefined literals such as Rust strings, and Hopper regex runs in a cancellable worker whose API remains usable after a deadline. However, that context is delivered as provider-specific trivia using names the schema never defines, and the description never explains why a pure search reports readOnlyHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and mode behavior are front-loaded, and most sentences earn their place with concrete caveats. The middle section is dense with provider-specific detail (Ghidra, Hopper) that partly restates the same warning about incomplete results, which could be consolidated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of return-value expectations, and it does address them qualitatively (deterministic and complete over defined objects, empty results not conclusive). It is missing any hint of result shape or volume limits, and the document parameter remains unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the four parameters are already documented and 3 is the baseline. The description adds some value by stating literal matching is the default and that Hopper regex mode uses ECMAScript Unicode syntax, which bears on the pattern parameter, but it says nothing about the document parameter or how case_sensitive interacts across modes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Search every provider-defined string object') and names the two matching modes, literal and regex, so the agent knows exactly what the tool does. It also scopes the result set ('provider-defined string objects... not every text sequence in artifact bytes'), which sharpens the intent, though it never contrasts itself with the sibling list_strings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit routing rule: 'If an address is known, read_bytes and xrefs inspect its bytes and references,' telling the agent when this tool is the wrong choice. The empty-result caveat ('an empty result does not prove text is absent') also sets expectations about when to escalate, but there is no stated guidance for choosing between this and list_strings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools