Recover the PlantUML source from a token or from any PlantUML render URL (the token is extracted automatically). Tokens use PlantUML's own 64-character alphabet ("0-9 A-Z a-z - _") over raw DEFLATE. This is NOT base64 - never encode or decode tokens with a base64 codec; use encode_source / decode_token.
| Name | Required | Description | Default |
|---|---|---|---|
| encoded | Yes | Token or full render URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It discloses the custom 64-character alphabet, raw DEFLATE encoding, automatic URL token extraction, and the base64 incompatibility. It does not explicitly describe return formatting or error behavior, but the core behavior is well covered.
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?
Three sentences, each earning its place: the first states purpose and input forms, the second explains technical encoding, and the third gives a critical warning. Information is front-loaded and there is no 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?
For a simple one-parameter tool with no annotations and no output schema, the description is quite complete: it covers input forms, algorithm details, and the correct sibling for encoding. The only minor gap is that the exact return representation is implied rather than explicitly stated.
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% and the schema already states 'Token or full render URL', so the baseline is 3. The description adds meaning by explaining that tokens are extracted automatically from URLs and by detailing the underlying encoding format, which helps an agent understand valid inputs beyond the schema.
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 uses a specific verb ('Recover') and a clear resource ('the PlantUML source') from explicit input forms: a token or a render URL. It distinguishes itself from the sibling encode_source by describing the inverse operation and naming encode_source directly.
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?
It states exactly when to use the tool ('from a token or from any PlantUML render URL'), names the alternative encode_source for the inverse operation, and gives an explicit when-not: never use a base64 codec. This is clear routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct responsibility: encoding/decoding tokens, rendering/validating diagrams, and retrieving syntax/reference information. The descriptions explicitly call out potential confusion points (e.g., token alphabet vs base64) and separate render from validate.
All tool names follow a consistent lowercase snake_case verb_noun pattern: decode_token, encode_source, get_syntax_reference, list_diagram_types, render_diagram, validate_diagram. This makes the tool set predictable and easy to navigate.
Six tools is well-scoped for a PlantUML-focused server: two token operations, two diagram lifecycle operations, and two reference/type lookup operations. There is no redundancy and no missing core capability that would require more tools.
The tool set covers the full diagram workflow: picking a type, getting syntax guidance, validating source, rendering output, and encoding/decoding shareable tokens. Agents can complete both common and advanced PlantUML tasks without dead ends.
