Eraser MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so comprehensively. It explains the tool's position in workflows ('Typically the final step after validate_diagram and/or fix_diagram'), describes the output format in detail ('Success message with diagram URLs', 'Image URL: Direct link to view/download', 'Edit URL: Link to open and edit'), and provides practical guidance about when content should be ready ('must be syntactically valid').

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 description uses a well-structured XML format with clear sections (purpose, when-to-use, when-not-to-use, examples, parameters, output-format, workflow-position). Every section serves a distinct purpose with no redundant information. The examples are practical and illustrate different usage scenarios efficiently.

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 4-parameter tool with no annotations and no output schema, the description provides exceptional completeness. It covers purpose, usage guidelines with sibling differentiation, parameter semantics with practical advice, detailed output format description, workflow positioning, and concrete examples. This fully compensates for the lack of structured metadata.

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 100%, so the baseline is 3. The description adds meaningful context beyond the schema: it explains that content must be 'complete diagram code in Eraser DSL format - must be syntactically valid' (emphasizing completeness and validity requirements), provides guidance on theme selection ('dark works well for most cases, light for print/documents'), and explains background parameter usage ('usually true unless user needs transparency'). However, it doesn't add significant value for diagramType beyond what the enum provides.

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 explicitly states 'Create and render diagrams on Eraser.io, returning URLs for viewing and editing' - a specific verb ('create and render'), resource ('diagrams on Eraser.io'), and output ('URLs for viewing and editing'). It clearly distinguishes this tool from its siblings (fix_diagram and validate_diagram) by emphasizing creation/rendering versus validation/fixing.

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?

The description provides explicit when-to-use and when-not-to-use sections with clear alternatives named (validate_diagram, fix_diagram). It gives specific scenarios for usage ('User asks to create, make, generate...', 'User provides complete diagram content') and exclusions ('User only wants to check if syntax is correct', 'Diagram content has known syntax errors').

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