context_oversharing_auditor__scan_text

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

With no annotations, the description carries the full behavioral burden, and it only describes what patterns are detected — not what is returned, whether findings carry severities/locations, whether scanning is read-only, or any limits. The pattern list is useful scope information but not behavioral disclosure.

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?

A single front-loaded sentence: the action and target lead, and the pattern enumeration trails as qualification. No filler sentences and nothing to trim without losing detection scope.

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 two-parameter text scanner with no output schema, the description is adequate on scope but silent on result shape and on how it differs operationally from scan_file/scan_directory. It is the minimum viable definition rather than a complete one.

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 100%, so both 'content' and 'label' are already documented in the schema. The description adds no syntax, format, or constraint detail beyond that, so the baseline of 3 for high-coverage schemas applies.

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 (Scan), a resource (agent/MCP source), and a named standard (OWASP MCP10:2025 context oversharing), then enumerates the exact defect classes it hunts (conversation dumps, unscoped memory tools, session-store leaks, prompt leaks, tool-result bleed, unfiltered vector queries). The enumeration lets an agent distinguish this from the sibling scan_file/scan_directory tools without opening a schema.

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?

Nothing says when to reach for scan_text over the sibling scan_file or scan_directory variants, nor what input shape it expects (inline text vs path). Usage is only inferable from the tool name. No prerequisites, no exclusions, no alternatives are named.

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