Search loot

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

Annotations already cover read-only/idempotent/non-destructive, but the description adds meaningful behavioral context beyond them: the credentials/ folder and known credential files are skipped, secrets are redacted by default, results are capped at max_matches, and paths come back relative. It also warns that returned content is untrusted scanned-system data and must not be treated as instructions, which is the exact safety caveat an agent needs for a secret-adjacent search tool.

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?

Four front-loaded sentences that each carry real information: capability, return format, filtering/redaction, and the safety warning. The trailing 'Read-only.' is the only redundancy, since readOnlyHint already declares it.

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?

With no output schema, the description steps in to say what comes back: matching lines with relative file paths, capped at max_matches, with credential paths skipped and secrets redacted. That covers everything an agent needs to call this correctly and interpret the response.

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 100%, so the schema already documents match, pattern, workspace, ignore_case, max_matches, and all_workspaces. The description restates the fixed-vs-regex default and the max_matches cap but adds no syntax or edge-case detail beyond the structured fields, which is the baseline-3 case.

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 specific verb and resource (search Sn1per loot files) plus the two modes it supports: literal string by default or POSIX extended regex. The scope statement (one workspace, or all only when all_workspaces is true) further sharpens the purpose, so an agent knows exactly what retrieval this performs.

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?

Gives a clear conditional rule for the risky parameter — all_workspaces only when the operator asks for a cross-engagement search — and describes the default single-workspace behavior. No sibling tool is named as an alternative, but none of the siblings (get_findings, get_ports, scan_status) overlaps enough to need an explicit exclusion.

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