memoryguard_audit

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

With no annotations, the description carries the full burden and discloses meaningful behavioral traits: read-only operation, no network access, no writes, and findings-with-evidence output. This gives an agent confidence about side effects beyond what the schema alone provides.

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 dense sentences with zero filler. The core safety property ('Read-only scan') is front-loaded, followed by scope, output, and constraints. Every clause 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 single-optional-parameter audit tool, this is complete: it covers what is scanned, what is returned, and the side-effect profile. No output schema exists, but the high-level return description is adequate for selecting and invoking the tool.

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?

The schema already documents the single optional 'workspace' parameter with 100% coverage, including its default value. The description adds no parameter-level detail, but the schema is sufficient, so the baseline of 3 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') and resource ('Agent workspace'), enumerates what is scanned (instructions, skills, memory, local RAG), and specifies the output ('findings with evidence'). The read-only framing clearly separates it from the many write-oriented memoryguard siblings.

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?

Provides clear context: this is a read-only audit scan of the local workspace, and the explicit 'No network, no writes' makes it obvious when it is safe to use. It does not name specific sibling alternatives or give when-not-to-use conditions, so it stops short of a 5.

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