Classify MCP tools as sensitive vs safe by glob policy

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

Goes well beyond the readOnlyHint/idempotentHint/destructiveHint annotations by disclosing: local glob match with no network access, no persistence, no Warden.vet call, empty patterns array → every tool safe, whole-name matching with '*delete*' hitting create_delete_repo, and that sensitive tools are classified but not run. These are exactly the behavioral traits an agent needs to predict side effects and edge cases.

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?

Organized into labeled sections (When to use / When NOT to use / Behaviour / Returns) that make it scannable, with the core purpose front-loaded in the first sentence. Slightly verbose, but every sentence carries distinct information — no filler, and the section labels justify the length.

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?

Complete for a 2-param tool with full schema coverage, rich annotations, and an output schema. The description covers purpose, when-to-use versus three named siblings, edge cases (empty patterns), safety profile (no network, no persistence), matching semantics, and return shape. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3. The description adds genuine value with a concrete worked example showing the call shape and return value ({ sensitive, safe }), and it reinforces the crucial nuance that descriptions/schemas are ignored in classification and only name is matched. The example clarifies the wildcard semantics beyond what the schema states.

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: 'Split advertised tool names into sensitive vs safe using the operator's case-insensitive * globs'. It names the policy source (policy.sensitiveToolPatterns), explicitly declares what it is not ('This is policy over identifiers, not an injection scan'), and the title itself is an accurate summary. Distinguishes clearly from siblings static_scan_tools, vet_mcp_server, and check_egress_url.

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 explicit selection criteria: 'When to use: show the user which names will need confirmation before they approve a server, or to preview a glob set.' Then gives explicit exclusions with named alternatives: 'When NOT to use: scanning descriptions for poisoning (static_scan_tools or vet_mcp_server); checking whether a URL is allowed out (check_egress_url).' An agent can route to the correct sibling without inference.

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