nvr_raw_call

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

With no annotations, the description carries the full burden and does so well: write-gate requirement for non-get methods, permanently refused modules, WARNING-level logging, VIGI_NVR_DRY_RUN support, and credential redaction in replies. The one gap is "both write gates," which is never enumerated, leaving the second gate ambiguous.

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?

Every clause earns its place: safety posture, alternative, exclusions, logging, dry-run, redaction. The load-bearing info (escape hatch + prefer nvr_call) is front-loaded and there is no filler.

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?

An output schema exists so return values need no explanation, and the description covers authorization, refusals, logging, and dry-run for a mutating raw-call tool. Only the ambiguous "both write gates" phrasing and the undocumented params object keep it from being fully complete.

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 only 25% (only confirm_write is documented), so the description must compensate and largely does: it explains method="get" vs. mutating methods and constrains the module namespace. The params object itself is left entirely unexplained, so the compensation is incomplete.

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?

Opens with a concrete metaphor plus mechanism ("Off-catalog escape hatch: send {method, module: params} directly"), so the agent immediately knows this bypasses the named-call catalog. It also explicitly names the sibling it is not ("Prefer nvr_call"), making it distinguishable without opening either schema.

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?

Gives an explicit alternative and preference ("Prefer nvr_call") plus hard exclusions (login and user_management always refused; non-get methods need write gates). It stops short of stating the positive condition under which the escape hatch is actually warranted (i.e. the method is missing from the catalog).

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