correlate_devices

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds substantial value beyond them: the per-device return shape, prioritization order, result_hash retention, and explicit privacy handling (host/IP/MAC/user/site fields stripped and listed under 'privacy'). It also states an honesty contract ('never call an empty, unresolved or partial result clean') that no annotation conveys.

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 purpose is front-loaded in the first sentence and the return/policy details are dense rather than padded. It runs long and restates the honesty rule twice ('Report needs_review and partial coverage honestly' / 'never call ... clean'), and enumerates return fields in prose where less would do, but almost every sentence 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?

With no output schema, the description must carry return-value semantics, and it does: resolution outcome, coverage, warnings, needs_review, result_hash, fix plan, prioritized findings with range source and vendor advisories. Privacy constraints and next-tool usage are also covered, so an agent has everything needed to invoke and interpret it.

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 the baseline is 3, but the description adds real meaning: vendor/product/version must be sent 'exactly as the inventory says,' no CPE is needed, and forbidden fields are stripped. The filters (max_findings, confirmed_only, etc.) are left to the schema, which documents them adequately.

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 (Find) plus the exact resource (CVEs affecting specific devices) and pins the scope to 'their exact firmware or software version.' This cleanly separates it from siblings like lookup_cve (single-CVE lookup) and get_fix_plan without needing to name them.

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?

'Use this for any specific device and firmware' gives a clear triggering context, and the note to keep result_hash 'for check_changes' routes the agent into the correct follow-up tool. It stops short of stating when NOT to use it (e.g. single-CVE questions belong to lookup_cve), so it is clear context rather than full when/when-not guidance.

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