mkt_voice

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the substance of what comes back (tone rules, hook patterns, ad-avoidance rules), which is real value beyond a bare name. It says nothing about whether the call is a read-only lookup or a generation step, what the response shape is, or whether the profile is cached per platform — gaps that matter with zero annotation coverage.

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?

One compact sentence with a colon-delimited breakdown of the three outputs; the core noun phrase is front-loaded. No filler, though the terseness is partly what creates the parameter ambiguity.

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 three parameters, one required, no annotations, and no output schema, the description should explain the inputs and roughly what a profile looks like. It covers the conceptual output but leaves the two optional parameters undefined and gives no sense of return structure, which is thin for a tool an agent must fill a schema for.

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% across three parameters, so the description must compensate and largely does not. '平台' in the text loosely maps to the required platform parameter, but 'hook' and 'what' — likely the draft opening and content under review — are never explained, so an agent must guess their meaning and format.

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?

The description names the resource precisely (platform tone profile plus hook/opening skeleton) and enumerates the three things it answers: how the platform speaks, how to write the opening, and what gets flagged as advertising. That separates it from the sibling mkt_voice_lint, which by name is the checking counterpart. It is a nominal phrase rather than a verb+object, so it is clear but not crisp about whether it retrieves or generates.

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?

Usage is only implied: an agent can infer you call this before writing copy for a given platform. There is no explicit when-to-use statement, no mention of when to prefer mkt_voice_lint or mkt_channels, and no stated prerequisites. Adequate but leaves routing to inference.

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