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

Annotations already declare a safe, idempotent read, so the description is free to add the parts annotations cannot: the returned object shape, that chapters is null unless status is "ready", what "not_requested" and "skipped" mean, and that thumbnailUrl is a public 360p JPEG. That is unusually rich context about outcomes and failure states.

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 its return shape, and every clause is substantive. The telegraphic style (braced type literal, bare quoted status values before they are explained) makes it slightly harder to parse than plain prose, but nothing is wasted.

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 no output schema, the description takes full responsibility for describing returns and does so completely: field list, nullability rule, thumbnail nature, downstream pointer, and status enumeration meanings. Nothing an agent needs to interpret the response is missing.

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% and all three parameters (jamId, intent, llm_model) are documented there. The description adds no meaning about jamId format or the intent/llm_model obligation, so it sits at the baseline where the schema carries the parameter burden.

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 ("AI chapters of a video Jam") and immediately distinguishes itself by declaring the exact return shape and by routing visual inspection to getFrames. An agent can tell it apart from getVideoTranscript or analyzeVideo 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?

Gives clear routing guidance for the visual case ("to look yourself, call getFrames with mode 'at' at the chapter's midpoint") and explains why output may be empty via the status semantics. It does not explicitly contrast with getVideoTranscript or analyzeVideo, which are the closest text/media siblings.

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