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

Goes well beyond annotations (readOnly=false, destructive=false, idempotent=false): it discloses the 4 MB request-body ceiling, that the call is asynchronous and returns a job_id immediately, the poll-then-download workflow (get_job_status → get_download_url), and how to distinguish Botverse structured errors from MCP/sandbox-layer failures. The non-idempotent, job-creating nature is implicitly reinforced by the polling workflow.

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, size limit, and alternatives are front-loaded in the first two sentences, which is ideal. The reliability/fallback paragraph is long and generic across all Botverse tools rather than specific to transcode_content, so it dilutes focus even though it carries real value.

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 an output schema present, the description need not explain return values, and it still covers the async lifecycle, size ceiling, and error semantics thoroughly. The only gap is the nested options object, whose sub-parameters are largely undocumented in both the schema and the description.

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 80%, so the baseline is 3. The description reinforces that content must be inline base64 under a 4 MB body and that encoding must be "base64," but says nothing about the nested options object (width, height, framerate, and others lack descriptions) beyond deferring to transcode_video.

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 — offload a video transcode by passing file bytes inline as base64 — and immediately contrasts with the upload-based path. An agent can distinguish it from transcode_from_url, get_upload_url, and transcode_video without opening any 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?

Explicitly names the use case (sandboxed agent environments that can't make HTTP uploads), the size constraint (<4 MB, short clips), and the concrete alternatives for larger files (transcode_from_url, or get_upload_url + transcode_video). It also gives an escalation path when calls fail.

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