read_guard_report

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

With no annotations, the description carries the disclosure burden, and it handles the critical points: it states read-only, notes that quarantined records are stored/exportable/erasable, and clarifies they are excluded from recall unless requested. It doesn't discuss output format or permissions, but for a zero-parameter report this is adequate.

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?

The description is compact and front-loads the scope ('What the read-path guards hold back'), then unpacks the two categories in the next sentences. Some phrasing ('the shapes that put it there', 'its share') is terse but not wasteful.

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 zero-parameter read-only report, the description supplies the essential decision data: what is reported, what metadata appears, and how it relates to recall. It stops short of stating the response format, but the absence of parameters and output schema lowers the burden.

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?

There are no parameters, so the schema cannot create ambiguity, and the description's content-level detail is the only semantic context needed. This matches the baseline 4 for a zero-parameter tool.

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 identifies the tool as a read-only report of what read-path guards hold back, then enumerates two exact record categories (quarantined and keyword-stuffed) and their associated metadata. This specificity makes it easy to distinguish from siblings like release_quarantine and recall.

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 phrase 'kept out of recall unless asked for' tells the agent this is the way to surface records that normal recall hides, which is a clear use context. It doesn't explicitly name 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.