modify_diagram

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

With no annotations provided, the description takes on the burden of behavioral disclosure. It explains that patches are deep-merged, lists are replaced wholesale, and typed diagrams are re-rendered from a spec. It does not explicitly mention side effects like file overwriting or irreversibility, but the modification behavior is substantially disclosed.

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 is well-structured: purpose first, critical prerequisite second, then the typed-diagram special case with a concrete example. It earns its length, though the phrase 'The node/connection operations below' is slightly awkward because those operations are in the schema, not literally below in the description.

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?

Given the tool's complexity and the existence of an output schema, the description covers most needed context: preconditions, diagram-type branching, and patch semantics. However, the update_spec/schema mismatch and the lack of explicit note about whether the file is saved in place leave a small but meaningful gap.

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 baseline is 3. The description adds meaningful semantics around update_spec patches and list replacement, but there is a notable inconsistency: the input schema's operations description lists only add_node, remove_node, update_node, add_connection, and remove_connection, while the description introduces update_spec as a valid operation. This creates ambiguity for an agent mapping the description to 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 clearly states a specific verb and resource: 'Modify an existing Excalidraw diagram created by this tool.' It distinguishes itself from create_diagram by emphasizing iterative editing of existing diagrams without recreation, and it lists concrete supported actions like adding components, removing nodes, updating labels, and rewiring connections.

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 gives explicit guidance: call get_diagram_info first before modifying, and it clearly separates typed diagrams (use update_spec patch) from architecture/flowchart diagrams (use node/connection operations). This tells the agent exactly when and how to use the tool relative to the diagram type.

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