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

The description adds useful behavioral context beyond the readOnlyHint annotation by disclosing the return format as a list of row objects keyed by header. It does not mention error handling (e.g., if no table matches) but the annotation covers the read-only nature, so the bar is lower.

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?

A single sentence that front-loads the verb and resource, then specifies the output shape. No wasted words.

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?

Given the simple single-parameter design and readOnlyHint annotation, the description covers the core purpose and output reasonably well. However, it lacks parameter semantics and usage guidance, making it only minimally complete for an agent trying to invoke it optimally.

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?

With 0% schema description coverage, the description must compensate for the 'selector' parameter, but it never mentions it. The default value 'table' is implicit, but the user gets no explanation about how to target a specific table or what a valid selector looks like.

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?

The description uses a specific verb 'extract' and a resource 'standard HTML table' with a clear output format 'list of row objects keyed by header'. This cleanly distinguishes it from sibling tools like get_text or get_html that return raw content.

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?

The phrase 'standard HTML table' implies a scope (probably not nested or malformed tables), but there is no explicit guidance on when to use this tool over alternatives, nor are any exclusions stated. The context of siblings is not leveraged in the description.

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