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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so restating 'read-only, no network, no stored state' is partly redundant. The added value is the concrete operating envelope (64 KB JSON input, 1 s per call, 1 MB result) and the determinism guarantee, which annotations do not express. Minor tension: the 64 KB input cap is stricter than the schema's 262144-char text maxLength, which an agent may notice.

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?

Each language version is front-loaded and wastes nothing: purpose, when, when-not, side effects, limits. The cost is that the entire block is duplicated in Spanish and English, roughly doubling length for an agent that only needs one.

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?

An output schema exists, so return values need not be described. With purpose, routing exclusion, determinism, side-effect profile and hard limits all present, nothing an agent needs to invoke this correctly is missing.

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, but the description earns more by specifying that the ellipsis counts toward the limit and that word-boundary cutting applies to grapheme mode — semantics an agent would otherwise have to guess from the schema. It does not cover the ellipsis max length or the 100000 cap on max, which remain schema-only.

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 (shortens text) plus the exact mechanism: maximum graphemes or words, optional word boundary, ellipsis counted toward the limit. It also names the sibling it is not (text-wrap), so an agent can route between the two without opening either schema.

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?

Explicit 'When:' clause (exact transform/compare/measure rather than approximation) and an explicit 'No para:' exclusion that names the alternative tool text-wrap and the condition that selects it. Both sides of the decision are covered.

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