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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: runtime (under 1 s), price (USD 0.001), a shared free-tier quota of 10 calls/IP/day, and an explicit no-logging/no-storage privacy guarantee. That is exactly the extra behavioral context annotations cannot convey.

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?

It is a single dense paragraph that is front-loaded with the purpose and output facets before inputs, pricing, and privacy. Long, but nearly every clause carries information the agent needs given there is no output schema; only the output-facet list could be trimmed slightly.

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?

There is no output schema, so the description carries the burden of describing returns, and it does so comprehensively (risk, positions, confusables, scripts, normalization status, optional normalized/stripped text). Quota, pricing, and data-handling are also covered, leaving nothing an agent needs to invoke it correctly.

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 80% schema coverage the baseline is 3, but the description names every parameter and adds meaning: the 200,000-character cap, the four normalization forms, and what stripping invisible characters actually removes. The only real gap is that normalize (the one schema param with no description) is listed without explaining the tradeoffs between forms.

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 (inspect) and resource (text for hidden/look-alike Unicode) and enumerates the exact output facets: risk level, invisible characters with positions, bidi/Trojan Source, UTS #39 confusables, combining-mark floods, scripts. This clearly separates it from siblings like text_stats, text_encode, or text_spellcheck.

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 'security-oriented' framing makes the use case evident and the description names concrete attack classes (prompt-injection smuggling, CVE-2021-42574) that motivate calling it. However, it never explicitly states when to prefer this over adjacent siblings or any when-not conditions, so it stops short of a 5.

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