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

Adds meaningful context beyond annotations: deduplicated lists, pricing model ($0.01/call, first 25 free, failed calls free), and an explicit 'reads or computes only and changes nothing' safety statement. It also explains why idempotentHint=false matters ('each call is charged, so repeats are not free'), which the annotation alone doesn't convey; only the exact return shape remains unstated.

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 list and use case, then example, then billing. Slightly dense on pricing detail and mildly redundant ('changes nothing' / 'each call is charged'), but every sentence carries information.

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 one-parameter, no-output-schema tool, the description covers inputs, output de-duplication behavior, and cost, which is enough to invoke it correctly. The precise output structure (list keys per category) is only implied by 'each list de-duplicated.'

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% for the single 'text' parameter, so the schema already documents it. The description's inline example (text=Mail ada@example.com ...) usefully shows accepted input form but adds no syntax or format rules beyond that; baseline 3 applies.

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) and enumerates the exact resource types (emails, URLs, phone-like strings, hashtags, @mentions, numbers), each de-duplicated. This clearly distinguishes it from nearby siblings like text_keyword_density or text_stats without opening their schemas.

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 concrete use case: 'pull contacts and links out of scraped pages or messages.' That sets clear context for when to reach for it, but it names no alternatives or exclusions (e.g., vs. regex_test or text_stats) for an agent choosing among siblings.

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