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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so the safety profile is covered structurally. The description still adds real behavior context beyond that: it discloses the index restriction, the conditional transcript timings ('when timings are stored'), and that query mode bypasses the normal read. It does not, however, say what happens for an id outside the index (error vs empty) or how large transcripts are actually chunked in the response beyond the offset mechanism.

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?

Front-loaded with the resource and the payload, then conditions, then the exclusion — a sensible order with no filler sentences. It is one very dense paragraph, though, and the channel list plus the repeated enumeration of returned fields makes it heavier than necessary for scanning.

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?

No output schema exists, so the description carries the return-value burden and does so fully: fields returned, timing behavior, passage-level links when query is used, and continuation via offset. For a 4-parameter read-only lookup limited to an internal index, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3; the description earns one step above by explaining the interaction semantics — that query 'replaces the plain read' and that offset exists specifically to 'keep reading a long transcript past the first part'. That said, these behaviors are largely restated from the schema's own parameter descriptions, so it does not add much genuinely new meaning.

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+resource (get a cached Canton Network video by YouTube id) plus the exact return payload (title, channel, publish date, description, transcript with timings). It also names the exact negative boundary — 'Does NOT fetch arbitrary YouTube videos' — so an agent can separate it from a generic YouTube fetch tool and from siblings like list_videos or search.

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?

Gives explicit when-to-use ('CANTON-ONLY and limited to videos already in CCPEDIA's index'), explicit when-not ('Does NOT fetch arbitrary YouTube videos (use a dedicated YouTube tool for that)'), and a prerequisite with the alternatives named ('Obtain ids from list_videos or search'). Nothing about tool selection is left to inference.

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