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

Annotations already declare readOnly, idempotent, non-open-world, non-destructive, so safety is covered. The description adds substantially beyond that: it discloses exact-lookup semantics (not guessing), that both spellings are stored per entry, and the failure mode (empty candidates for unknown words or ambiguous script). That failure-mode disclosure is exactly the kind of non-obvious behavior 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?

Front-loads the core operation, then the bidirectional behavior, then the exact-lookup caveat and failure mode. Four sentences, each carrying distinct information with no repetition; the size is proportionate to a tool whose main risk is caller misuse (multi-word input, expecting guesses).

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?

Output schema exists, so return values need not be explained, and they aren't. For a 2-param read-only transliteration tool, the description covers input constraints, behavior, the override, and the failure mode, leaving no evident gap an agent would need to fill.

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 schema documents both params, calling for a baseline of 3. The description adds value by defining `text` as ONE word (not a phrase, no tokenization) and by stating the edge-case return for `target` auto-detection, which goes beyond the schema's prose. It does not add further syntax detail for `target`, so not a 5.

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 (transliterate), resource (one Interslavic word), and scope (Latin↔Cyrillic, single word not phrase). The parenthetical '(not a phrase — the lookup does not tokenize)' and the explicit contrast with 'deromanize tools' sharply distinguish it from siblings like anglo_romanize and slavonic_transliterate.

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?

Explicitly states the auto-detect behavior and the `target` override condition ('or pass target to force it'). It also names the class of alternative it is NOT like ('the lossy deromanize tools') without naming a specific sibling, which is clear context but without a precise 'use X instead when Y' pointer.

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