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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower. The description does add genuinely non-structured facts: the 2-credit cost and the two scoring modes plus differing-word statistics. However, since an output schema exists, the return-value enumeration is largely redundant, and nothing is said about ordering sensitivity or edge cases such as identical or empty inputs.

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 dense sentence that front-loads the core operation and folds in outputs and cost with no filler. The only waste is the redundant 'Text Similarity: Text Similarity' echo of the title before the real content begins.

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 simple two-string, read-only tool with full schema coverage and an output schema, the definition supplies what an agent needs: what it computes, both scoring modes, and the credit cost. The remaining gap is the absence of any routing hint toward LevenshteinDistance or SpellChecker, which matters given how crowded this sibling namespace is.

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% — both text1 and text2 are documented with the <1000 character limit and examples. The description adds nothing beyond the schema: it does not say whether argument order affects results, whether whitespace is normalized, or how the 1000-character limit is enforced. Baseline 3 applies when the schema carries the parameter burden.

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 and resource: 'compares two text strings and calculates their percentage match score', and enumerates the outputs (case-insensitive and case-sensitive scores, differing-word count and proportion). This is clear enough to distinguish it from most siblings, though it never mentions LevenshteinDistance, the closest functional neighbor.

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 when-to-use guidance at all: no statement of what task this suits (fuzzy dedupe, near-duplicate detection, answer grading) and no exclusion or comparison against LevenshteinDistance, which also compares two strings. The only situational note is a credit cost, which is pricing rather than usage guidance.

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