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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower, and the description adds meaningful behavioral context beyond them: a per-call price ($0.05) and the x402/USDC-on-Base payment mechanism, plus the pre-comparison normalisation pipeline. It does not state rate limits, failure behavior on over-length input, or whether the 512-char cap is enforced pre- or post-folding.

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?

Purpose is front-loaded in the first clause and the long enumeration is dense but informative rather than redundant. Slightly heavy for two sentences, and the pricing/payment sentence could arguably be a separate line, but nothing is wasted.

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 carry the return shape, and it does so by listing exactly which measures come back, including phonetic keys for each string. Pricing and payment are disclosed. Minor gaps remain on error handling and whether `only` filters affect the returned object structure, but the agent has enough to call 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?

Schema coverage is 100%, so the baseline is 3, and the description earns a bump by enumerating the measure names (Levenshtein, Damerau-Levenshtein, Jaro, Jaro-Winkler, LCS, Dice bigrams, Soundex, Metaphone, NYSIIS) – effectively the valid domain for the `only` parameter, which the schema leaves as an opaque “comma-separated measure names.” It also explains what folding does semantically, though it omits the `punct` fold the schema lists.

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?

Names a specific verb and resource (“compare two strings”) and enumerates the exact measures returned, so an agent knows this is the string-similarity tool and not a slug/transliterate/unicode sibling. The scope (every standard similarity measure in one call) is unambiguous.

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?

Usage is implied by the description – you call it when you need to compare two strings – but it gives no explicit when-not-to-use guidance, no alternatives among the text_* siblings, and no mention of batching or when to prefer one measure. Nothing is misleading, but routing guidance is thin.

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