Assess saved activity snapshots with local rules to return findings, suppressions, assessment gaps, and visibility caveats; empty results do not confirm safety.
Assess a saved snapshot with local rules. Returns findings, visible suppressions, assessment gaps and visibility caveats. Empty findings do not establish safety. limit is 1–100.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| snapshot_id | Yes | ||
| min_severity | No | info |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value-added content is the return surface (findings, suppressions, assessment gaps, visibility caveats) and the key caveat that empty results are not proof of safety — meaningful context with no output schema. It stops short of 5 by not explaining what suppressions or gaps actually represent.
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 short sentences, front-loaded with purpose and packed with non-redundant information; the safety caveat and limit range both earn their place. Slightly dense jargon ('visibility caveats', 'assessment gaps') is the only minor cost.
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 read-only, annotation-covered tool with no output schema, the description covers the return surface and a critical interpretation caveat. It remains incomplete on min_severity semantics and on result handling (no mention of pagination or what ordering the limit applies to), which an agent needs to call it correctly.
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 0%, so the description must carry parameter meaning. It only adds the 'limit is 1–100' constraint; snapshot_id's role is merely implied and min_severity — its default, allowed values, and filtering effect — is completely undocumented anywhere.
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 concrete verb and resource ('Assess a saved snapshot with local rules') and names the outputs (findings, suppressions, gaps, caveats). It implicitly distinguishes itself from take_snapshot (this operates on an already-saved snapshot) but never names a sibling explicitly, so it stops short of a 5.
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 'saved snapshot' implies this runs after take_snapshot, and 'Empty findings do not establish safety' is useful interpretive guidance. But there is no explicit when-to-use/when-not-to-use statement and no routing to alternatives like compare_to_peers or suggest_removals, leaving usage inferred rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.