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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description goes beyond them by disclosing what is deliberately withheld (provider tokens, download URLs, administrative errors, transcript body) and by qualifying availability as "reported". That negative-space disclosure is genuinely useful for an agent deciding whether it has to call another tool for a download URL or transcript.

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?

Two tight sentences with no filler; the positive return contract comes first and the exclusions second. The list of fields is dense but each item is doing discriminating work.

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 not be explained, yet the description still usefully frames the return surface and its gaps. What is missing for a single-parameter lookup is the not-found/error behavior and any note on the open-world data source; those are the only meaningful holes given the tool's simplicity.

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 0%, so the description must carry the parameter meaning. "A returned videoId" does add real semantics the bare integer schema lacks — that the value must originate from an earlier result rather than being constructed — but it says nothing about the integer type, the positive-value constraint, or what happens with an invalid id.

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 uses a specific verb ("Read") plus an enumerated return set (title, description, channel, published date, duration, availability, links) tied to a single videoId, so the operation is legible without opening the schema. It also carves out the transcript case ("no ... transcript body"), which partially separates it from get_comedy_transcript, but it never names that sibling or states plainly that this is the metadata lookup for a comedy video.

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?

"Read a returned videoId" implies the id must come from a prior search/list call, which is useful implied guidance, and the transcript exclusion hints at the alternative for transcript content. However, there is no explicit when-to-use/when-not-to-use statement, no mention of prerequisites, and no routing to get_comedy_channel or get_comedy_special for related data.

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