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

Goes beyond annotations by disclosing the credit cost model and its conditionality ("uses credits only when the transcript is not stored yet"), which is exactly the kind of side effect an agent needs before calling a tool annotated readOnlyHint=false. It also states the return payload (text and language). It does not cover latency or whether a stored transcript is cached per-post, but nothing contradicts the annotations.

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-loads the core action, then routing, then the misuse case, then return values and cost. Every sentence carries distinct information; no restatement of the title or name.

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 still names the return payload (text plus language); with three optional, mutually-exclusive-looking params it explains where each key comes from and what to do instead for links. The credit disclosure closes the remaining question an agent would have before invoking 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 coverage is 100%, so baseline is 3, but the description adds genuine meaning beyond the schema: each key is tied to its originating tool (find_viral_posts, list_inspiration), and it clarifies what the parameters are NOT ("It takes those keys, not a link"). That negative constraint is not expressible in the schema properties.

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 ("Returns the spoken words of a post") and immediately names the two key shapes it accepts and the siblings that produce them. An agent can distinguish it from generate_content's source_url path and from get_generation 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 explicit when-to-use ("read a post before remixing it with generate_content") and explicit when-not-to-use with the alternative named ("for a pasted link, generate_content with source_url reads the video itself"). The routing decision between the two tools is fully specified.

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