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

Beyond the annotations (readOnly, non-destructive, idempotent), the description discloses statelessness, a 32 KB payload ceiling, a 60 RPM rate limit, the '?demo=true' and L402 (100 sats) access paths, and the HTTP 400 failure mode. Those are exactly the operational facts an agent needs and none are in the structured fields.

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 purpose and the sibling routing rule, then the operational constraints. It is dense and slightly runs-on in the final parenthetical clause, but every sentence carries information that is not duplicated elsewhere.

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 tool with an output schema, the return values need no explanation. Combined with the auth/payment path, rate and size limits, and error behavior, nothing material is missing for correct invocation.

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 the enum is documented in-schema, so the baseline is 3. The description only restates the 'modality_focus' default and the nature of 'input' without adding format or syntax guidance beyond the schema.

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 (analyzes) plus the exact resource (combined multimodal prompts spanning text, image descriptors, audio transcripts, and video temporal events) and names the underlying model. It also distinguishes itself from the sibling generate_gemini_completion, so an agent can route without opening either 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?

Explicit when-to-use ('correlating information across multiple media modalities in a single reasoning pass') and an explicit when-not with the named alternative ('for running pure text-only reasoning or coding prompts, use generate_gemini_completion instead'). Nothing 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.