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

Annotations already declare readOnlyHint and destructiveHint=false, but the description adds real context beyond them: pricing model, first 25 free, failed calls free, and that each call is charged so repeats are not free. That last point usefully explains the non-idempotent cost profile. Return format is not described, but no output schema exists.

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-loaded with the transformation, then semantics, use cases, and finally billing constraints. Dense but nearly every sentence carries distinct information; the billing sentences are slightly long relative to the core task.

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 3-parameter transform tool with full schema coverage and annotations, the description covers behavior, edge cases (case, punctuation), usage and cost. The only minor omissions are explicit sibling routing and any hint of output shape, which is acceptable without an output schema.

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 does add meaning: it clarifies that the default shift of 13 is ROT13, that case is preserved, digits and punctuation are untouched, and that decode=true reverses the shift. It adds an example invocation, though it does not reconcile the schema's -25..25 range with 'shifted by 1-25 places'.

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 ('Encode or decode text with a Caesar cipher') plus the exact transformation semantics (A-Z, 1-25 shifts, default 13 = ROT13). It doesn't name the closest siblings (base64_encode/decode, text_morse, hash), but 'it is not encryption' does steer an agent away from misusing it as a crypto tool.

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?

Gives concrete use cases (puzzles, spoiler hiding, teaching) and an explicit exclusion ('it is not encryption'). It stops short of pointing to the alternative tools an agent should pick instead, e.g. base64_encode or text_morse.

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