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

Annotations already declare readOnly/destructive/idempotent/openWorld, but the description adds real value beyond them: per-list de-duplication, the per-call charge with 25 free and failed calls free, and the warning that repeats are not free. The 'changes nothing' clause largely restates readOnlyHint, keeping it just under 5.

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 the extraction targets, then usage, then an example, then pricing. Every sentence is relevant to selection or cost, though the pricing/credit-key sentence is dense and could be split for readability.

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 must convey the return shape; it does so by naming each category as its own de-duplicated list. Cost and safety are covered, leaving only minor gaps such as whether matches are returned in order of appearance.

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?

Only one parameter and schema coverage is 100%, so the schema baseline of 3 applies. The description's inline example (text=Mail ada@example.com ...) usefully shows the input format, but it does not add format or size constraints beyond that.

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 (Find/extract) plus the exact set of resource types it returns: emails, URLs, phone-number-like strings, hashtags, @mentions and numbers. This is far more specific than siblings like text_stats or text_diff, so an agent can route to it without opening the 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 a clear use context ('pull contacts and links out of scraped pages or messages') and a worked example string. It does not name exclusions or alternatives (e.g., use text_stats for counting, html_to_text for markup stripping), so it stops short of full when/when-not guidance.

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