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

Goes well beyond the annotations by disclosing output construction rules (headers as keys, raw arrays when no header), colspan repetition, entity decoding, caption handling, and a 500 KB input cap. It also explains the billing model and clarifies why repeats are not free, which explains the idempotentHint=false annotation rather than contradicting it.

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 transformation and output shape in the first sentence, then adds usage, then pricing. The pricing sentence is long and packs several facts, but each sentence carries distinct information with no 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?

No output schema exists, yet the description fully specifies the return shape, including the no-header fallback to raw arrays. For a single-parameter tool with full annotation coverage, nothing needed to call it correctly 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?

There is only one parameter and schema coverage is 100%, so the schema already documents 'html' fully. The description restates the 500 KB limit and that the HTML itself is the argument but adds no new syntax or format 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 and resource ('Extract every table from an HTML fragment into JSON') and describes the output shape. It is clearly separable from siblings like csv_to_json and html_to_text because the input is HTML tables and the output is structured JSON rows.

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 concrete use cases ('turn web or email tables into data an agent can sort and compute on') and routes the agent elsewhere for fetching a page ('to fetch a page first use extract'). It lacks an explicit when-not-to-use versus html_to_text, and the referenced 'extract' tool does not appear in the sibling list, but the selection context is clear.

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