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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context — and it does, disclosing the $0.003 USDC per-call price on eip155:8453 via x402, plus the English-only limitation of the Flesch scores and the stop-word filtering on keywords. That pricing and language-scope disclosure is the kind of behavioral fact an agent cannot get from annotations, though the response shape is only enumerated rather than described.

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?

The single dense paragraph front-loads the metric inventory before the pricing caveat, which is the right order. The main waste is the opening clause repeating the title verbatim, and the semicolon-chained metric list is long but each clause adds a distinct capability rather than 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 effectively serves as the return-value spec by enumerating every computed statistic, and it adds the payment and language constraints an agent needs before invoking. The one meaningful gap is `top` — how many keywords come back and how to control that — which leaves the agent guessing at a tunable knob.

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 0%, so the schema gives only types, defaults and bounds with no prose, and the description does not compensate: the `top` parameter (default 10, max 100) is never named or explained, and the 1 MB `text` maxLength constraint is not mentioned. The phrase 'most frequent keywords' is the only hint at `top`'s purpose, and it never states how many keywords are returned by default.

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?

The description names a concrete resource (text) and enumerates the exact metrics computed — characters, graphemes, words, sentences, paragraphs, lines, reading/speaking time, Flesch and Flesch-Kincaid scores, and keyword frequency. That specificity separates it cleanly from the nearest siblings, text_diff and text_transform, which analyze or alter text rather than quantify it.

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 metric list: an agent can infer this is the tool for counting/readability on a block of text. However, there is no explicit routing guidance — no statement of when to prefer it over text_transform or text_diff, and no note on what to do with non-English input beyond the parenthetical '(English)' attached to the readability formulas.

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