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

Annotations declare a non-read-only, destructive, open-world, non-idempotent operation; the description substantiates that by disclosing the write side effect (result is stored in the knowledge base unless saveToKnowledge is false), the cost/credit implication, and the dual return path (stored AND returned here). It also discloses per-mode sourcing behavior (YouTube English captions, TikTok native captions vs speech-to-text fallback), which annotations cannot express.

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 core purpose, then mode-by-mode behavior, then cost and storage effects — a sensible order with no filler sentences. The parenthetical transcription detail is dense but each clause carries distinct information, so it is only mildly long rather than padded.

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 a 4-parameter, open-world mutation with no output schema, the description covers the important unknowns: cost, storage side effect, and that text is returned directly. It doesn't mention failure modes (private/unsupported URLs, missing captions causing STT fallback limits) or rough output shape, which would complete it.

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 every parameter (title, value, sourceType, saveToKnowledge) is already documented structurally. The description reiterates the same meanings — what value means per sourceType and what saveToKnowledge toggles — without adding syntax, format, or validation detail beyond the schema. Baseline 3 applies when the schema carries the load.

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 (turns a video/audio/question into text) and then enumerates all four sourceType modes with what each one reads. An agent can tell it apart from ingestion siblings like add_knowledge_from_url and from the paired estimate_source_cost without opening a 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 a concrete prerequisite ('quote it first with estimate_source_cost') and frames the use case ('text to write from'), which orients the agent well. It stops short of explicitly excluding add_knowledge_from_url / add_knowledge_from_file, which also ingest URLs and are the nearest ambiguous siblings.

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