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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely useful behavior beyond them: a 20,000-character truncation limit and a per-call cost of $0.008 USDC via x402. It omits what happens when both url and text are supplied, or when neither is, which matters given zero required parameters.

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?

Two compact sentences, front-loaded with the capability and output categories, followed by the two hard operational facts (truncation, price). 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?

With no output schema, the description compensates well by enumerating the entity types returned. The remaining gap is the input-selection rule for url vs text, which an agent calling with zero required params would need.

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 0%, so the description must carry both parameters. 'from text or a URL' conveys that url and text are alternative inputs, but it does not state precedence or mutual exclusivity, leaving the two-parameter contract partly ambiguous.

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+resource (named-entity extraction) and enumerates the exact output categories (people with roles, orgs by type, places, ISO dates, money, products, events, topics, emails/URLs/hashtags), which is unusually informative. It does not, however, differentiate itself from adjacent siblings such as extract, structure, or pii_redact, so it stops short of a 5.

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?

There is no explicit when-to-use guidance and no named alternative, despite several plausible siblings (extract, structure, summarize, pii_redact). The only routing signal is the implicit input constraint (text or URL), which the agent must infer.

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