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

With no annotations, the description carries the full behavioral burden. It usefully discloses cost ($0.015 USDC on Base) and filtering logic (rejects office PSTN landlines, detects phantom wa.me/linktr.ee links), which is real value. However it omits whether the call fails without paymentSignature, whether charging happens per-call or per-success, and any latency/rate/failure behavior for what is clearly a paid external enrichment call.

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 front-loaded sentence that opens with the verb and purpose before piling on the capability list; no filler or restatement of the name. Slight deduction because the pricing clause is grafted onto the end of the capability list, blurring extraction scope with billing terms.

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 what comes back, and it does so indirectly by listing the extracted entities. But it never describes the response shape (per-field nulls, confidence, partial results on failure) or the payment flow prerequisites, which matters for a paid three-parameter tool with no annotations.

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 description coverage is 100%, so the schema already documents url, businessName, and paymentSignature fully, establishing a baseline of 3. The description adds only marginal semantic color — 'sanitize brand names' loosely maps to businessName and the USDC price hints at paymentSignature — without explaining accepted formats or how payment signatures interact with the charge.

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 (enrich) and resource (business URL/lead) and then enumerates the concrete outputs: brand sanitization, phantom link detection, E.164 phone extraction, emails/socials, and CMS/analytics pixel detection. This is unmistakably distinct from siblings like generate_outreach_dossier or extract_clean_markdown.

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 'for SDR/sales outreach' implies the context of use, but there is no explicit when-to-use/when-not guidance and no reference to a sibling alternative (e.g. generate_outreach_dossier, which likely consumes this output). The agent must infer selection from the description alone.

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