vk_call_raw

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

Annotations already flag readOnlyHint=false and destructiveHint=true; the description adds real value beyond them by explaining the per-verb safety model (GET=read, POST/PUT/PATCH=write, DELETE=destructive) and the confirmation parameters. It does not conflict with annotations (the global destructive flag is simply conservative), but it omits auth requirements and rate-limit/pagination behavior for a very open-ended tool.

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?

Purpose is front-loaded, followed by the safety model, an Args block, and a one-line Returns note. Structure is clean and scannable; the 'Returns JSON' line is minor redundancy given an output schema exists, but nothing is egregiously 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?

Given 7 parameters, 0% schema coverage, and a present output schema, the description covers parameters and return shape adequately and need not re-explain return values. It stops short of stating authentication/prerequisite requirements, which is the main missing piece for a tool that can hit arbitrary endpoints.

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 the parameter burden, and it does: method (with accepted verbs), path (with a concrete path example), host (defaults to service host), query, body, and the two confirmation flags. The confirmation parameters are only described as 'confirmations' without stating when each is required, which is the only meaningful gap.

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 ('Execute ANY endpoint') and immediately scopes it with 'even ones not in the catalog (full API coverage)', which distinguishes the raw escape hatch from the catalog-based siblings like vk_call_method/vk_describe_method. An agent can tell what this tool is for without opening the 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?

The '(even ones not in the catalog)' clause implies when to reach for this over the catalog tools, and it points to a confirmation-rules sibling. However it never explicitly says 'use this instead of vk_call_method when the endpoint is unlisted', and the referenced '{svc}_call_method' placeholder is unresolved, so the routing is left partly to inference.

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