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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds substantial behavior beyond them: normalization via 'existing transcription rails', the three-output contract, filler-removal/wording-preservation rules, the call-source masked-summary caveat, and 'All outward outputs are mask-gated.' This is consistent with readOnlyHint (compute without mutation) and goes well beyond what annotations alone convey.

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?

A single dense paragraph, front-loaded with the action verb and carrier list, with the exclusivity constraint stated immediately after. Every clause carries information — carrier list, one-carrier rule, transcript rail, three outputs, call caveat, mask-gating, business gating — and the length is justified by the tool's 11-parameter complexity, though tighter phrasing would improve scannability.

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?

For an 11-parameter orchestrator with nested objects, an output schema, and 100% schema coverage, the description covers the input domain, exclusivity rule, processing pipeline, content of every output, and both conditional behaviors (call sources, business context) plus mask-gating. Nothing an agent needs to decide whether or how to call it is omitted at this complexity level.

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 baseline is 3; the description adds value by grouping the five carriers, declaring the mutual-exclusion invariant ('Provide exactly ONE input carrier'), clarifying that text and notes merge, and mapping real-world input types to the correct carrier parameter. These semantics are not fully obvious from the individual parameter descriptions alone.

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 — 'Run the voice intelligence orchestrator' — then enumerates the full input domain (audio/video file, public URL, PDF, image, text/notes) and the three composed outputs (summary, actual script, authority report). This clearly differentiates it from the growthos_* and talent_scout_* siblings without needing to inspect their schemas.

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 'over any input' phrasing plus the explicit five-carrier enumeration gives clear context for when the tool applies, and the 'Provide exactly ONE input carrier' constraint is unambiguous. However, it never names an alternative to prefer when only a single deliverable is needed (e.g., growthos_owner_facing_report for an owner report alone), so explicit when-not routing is missing.

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