get_live_captions

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

Goes well beyond the readOnly/idempotent annotations: it discloses that translations are a re-translated rolling window rather than a stored record, that the cursor applies only to spoken-language text, and that output is wrapped in <untrusted-text> and should be treated as data rather than instructions. That prompt-injection warning is exactly the kind of behavioral context 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?

Five short sentences, front-loaded with what the tool returns and the translation-window caveat before the cursor mechanics and safety note. Dense but every sentence carries information; the closing 'Returned text is sent to the AI model you are using' is the one line that is arguably generic filler.

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 correctly shoulders the return-value burden: it describes the text shape, the untrusted wrapper, and the translation window's mutability. It leaves unaddressed the edge cases an agent would want (no captions yet, invalid language code, whether cursor is ignored for translations), which keeps it short of a 5.

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 baseline is 3; the description still adds value by tying the cursor to spoken-language output only, reinforcing and clarifying the schema's constraint in context. It does not add format or syntax details for language or maxChars beyond the schema, keeping it just above baseline.

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?

Opens with a specific verb and resource ('The newest live caption text of a stream') and clarifies it can be the spoken language or a translation. It implicitly separates itself from get_saved_transcript by calling translations 'not a stored record', but never names the sibling, so the differentiation is inferential rather than explicit.

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?

It gives concrete in-tool guidance for the cursor ('Pass the returned cursor back to get only new spoken-language text'), which tells the agent how to poll incrementally. However, it never says when to pick this over get_saved_transcript or get_session_overview, and offers no exclusions or prerequisites.

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